public inbox for [email protected]help / color / mirror / Atom feed
[PATCH v32 3/6] Subscripting for jsonb 203+ messages / 4 participants [nested] [flat]
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v30 3/6] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index b961d29472..ad364b4a0e 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 04b70c805b..adcf16acf1 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index f92861d8d2..538740aec9 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1461,13 +1478,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1482,9 +1495,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1509,7 +1541,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1525,22 +1557,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1558,7 +1593,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1568,11 +1606,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1594,9 +1636,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1607,6 +1652,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4166,58 +4237,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4489,7 +4508,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4646,7 +4666,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4809,7 +4830,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4862,11 +4883,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4883,7 +4904,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4914,7 +4935,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4937,7 +4958,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4969,7 +4990,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5017,7 +5038,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5033,7 +5054,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5044,7 +5065,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5078,12 +5099,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 6de2dd29f1..36637afefb 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10707,6 +10707,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '4191', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '4192', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index f868a6d52e..64c0c6d519 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -447,7 +447,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --g5st7yssq7xavhfb Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v30-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v35 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index d370348a1c..37508061a1 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4794,7 +4815,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4847,11 +4868,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4868,7 +4889,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4899,7 +4920,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4922,7 +4943,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4954,7 +4975,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5002,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5018,7 +5039,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5029,7 +5050,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5063,12 +5084,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 2c6aa65bf8..abcbf97d05 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10898,6 +10898,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --evj76j7ekwacmcsz Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v35-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v32 3/6] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --xuxpg5p32zizz4zy Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v32-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v31 3/6] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 04b70c805b..adcf16acf1 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index ba9c61307e..6f73d8ecc8 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10862,6 +10862,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '4226', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '4225', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index c151c0b37b..6286461be5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bvn7grlx53cj2mie Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v31-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v29 3/6] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 231 ++++++++++++++++++++ src/test/regress/sql/jsonb.sql | 66 ++++++ 8 files changed, 630 insertions(+), 108 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 9927d0879a..2de897342c 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 8b73903160..7be928fe2f 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -67,18 +67,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -562,6 +573,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -572,9 +607,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 1b0fb2afae..408ca7d9b2 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -20,12 +20,16 @@ #include "catalog/pg_type.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonapi.h" #include "utils/jsonb.h" @@ -457,18 +461,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -483,6 +491,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * SQL function json_object_keys * @@ -1328,13 +1345,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1349,9 +1362,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, 'i', &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1376,7 +1408,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1392,22 +1424,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1425,7 +1460,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1435,11 +1473,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1461,9 +1503,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1474,6 +1519,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4033,58 +4104,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4356,7 +4375,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4447,7 +4467,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4610,7 +4631,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4663,11 +4684,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4684,7 +4705,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4715,7 +4736,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4738,7 +4759,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4770,7 +4791,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4818,7 +4839,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -4834,7 +4855,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -4845,7 +4866,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -4879,12 +4900,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index ab5320622e..5045afab8b 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10663,6 +10663,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '4191', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '4192', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 8b2b61ca4b..3925ecaf97 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -447,7 +447,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5e8179665e..6081fabb74 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a2a19f8104..c7d7e30b45 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4640,6 +4640,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index efd4c45185..934fa9d67a 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1183,6 +1183,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --adquyx6kg5n26q6j Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v29-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v33 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 8761597e12..bf0d4ef743 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --u66dlpg6gaevsofr Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v32 3/6] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 231 ++++++++++++++++++++ src/test/regress/sql/jsonb.sql | 66 ++++++ 8 files changed, 630 insertions(+), 108 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 5a09d65fdc..f46a2828b3 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4796,7 +4817,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4849,11 +4870,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4870,7 +4891,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4901,7 +4922,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4924,7 +4945,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4956,7 +4977,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5004,7 +5025,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5020,7 +5041,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5031,7 +5052,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5065,12 +5086,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 1577cb9ab8..825cb7d1c5 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10879,6 +10879,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '4191', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '4192', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..ecfaaebe06 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..dc6f741d08 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --ques2rolqe435p6o Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v32-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v34 3/5] Subscripting for jsonb @ 2019-02-01 10:41 erthalion <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: erthalion @ 2019-02-01 10:41 UTC (permalink / raw) Subscripting implementation for jsonb. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. Reviewed-by: Tom Lane, Arthur Zakirov --- src/backend/utils/adt/jsonb.c | 27 ++- src/backend/utils/adt/jsonb_util.c | 76 ++++++- src/backend/utils/adt/jsonfuncs.c | 325 ++++++++++++++++++++-------- src/include/catalog/pg_proc.dat | 8 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 2 + src/test/regress/expected/jsonb.out | 233 +++++++++++++++++++- src/test/regress/sql/jsonb.sql | 68 +++++- 8 files changed, 632 insertions(+), 110 deletions(-) diff --git a/src/backend/utils/adt/jsonb.c b/src/backend/utils/adt/jsonb.c index 1e9ca046c6..f66642def3 100644 --- a/src/backend/utils/adt/jsonb.c +++ b/src/backend/utils/adt/jsonb.c @@ -1134,23 +1134,34 @@ to_jsonb(PG_FUNCTION_ARGS) { Datum val = PG_GETARG_DATUM(0); Oid val_type = get_fn_expr_argtype(fcinfo->flinfo, 0); - JsonbInState result; - JsonbTypeCategory tcategory; - Oid outfuncoid; + JsonbValue *res = to_jsonb_worker(val, val_type, false); + PG_RETURN_POINTER(JsonbValueToJsonb(res)); +} - if (val_type == InvalidOid) +/* + * Do the actual conversion to jsonb for to_jsonb function. This logic is + * separated because it can be useful not only in here (e.g. we use it in + * jsonb subscripting) + */ +JsonbValue * +to_jsonb_worker(Datum source, Oid source_type, bool is_null) +{ + JsonbInState result; + JsonbTypeCategory tcategory; + Oid outfuncoid; + + if (source_type == InvalidOid) ereport(ERROR, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("could not determine input data type"))); - jsonb_categorize_type(val_type, + jsonb_categorize_type(source_type, &tcategory, &outfuncoid); memset(&result, 0, sizeof(JsonbInState)); - datum_to_jsonb(val, false, &result, tcategory, outfuncoid, false); - - PG_RETURN_POINTER(JsonbValueToJsonb(result.res)); + datum_to_jsonb(source, is_null, &result, tcategory, outfuncoid, false); + return result.res; } /* diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index d370348a1c..37508061a1 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -21,12 +21,16 @@ #include "common/jsonapi.h" #include "fmgr.h" #include "funcapi.h" +#include "executor/execExpr.h" #include "lib/stringinfo.h" #include "mb/pg_wchar.h" #include "miscadmin.h" +#include "nodes/nodeFuncs.h" +#include "parser/parse_coerce.h" #include "utils/array.h" #include "utils/builtins.h" #include "utils/hsearch.h" +#include "utils/fmgroids.h" #include "utils/json.h" #include "utils/jsonb.h" #include "utils/jsonfuncs.h" @@ -460,18 +464,22 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); +static Datum jsonb_set_element(Datum datum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null); +static Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -486,6 +494,15 @@ static void transform_string_values_object_field_start(void *state, char *fname, static void transform_string_values_array_element_start(void *state, bool isnull); static void transform_string_values_scalar(void *state, char *token, JsonTokenType tokentype); +static SubscriptingRef *jsonb_subscript_prepare(bool isAssignment, + SubscriptingRef *sbsref); + +static SubscriptingRef *jsonb_subscript_validate(bool isAssignment, + SubscriptingRef *sbsref, + ParseState *pstate); +static Datum jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate); +static Datum jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate); + /* * pg_parse_json_or_ereport * @@ -1447,13 +1464,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1468,9 +1481,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +static Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + Jsonb *res; + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + JsonbValue tv; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1495,7 +1527,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1511,22 +1543,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1544,7 +1579,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1554,11 +1592,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1580,9 +1622,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1593,6 +1638,32 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Datum jsonbdatum, Datum *path, int path_len, + Datum sourceData, Oid source_type, bool is_null) +{ + Jsonb *jb = DatumGetJsonbP(jsonbdatum); + JsonbValue *newval, + *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + newval = to_jsonb_worker(sourceData, source_type, is_null); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4152,58 +4223,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4475,7 +4494,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4633,7 +4653,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4794,7 +4815,7 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, static JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4847,11 +4868,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4868,7 +4889,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4899,7 +4920,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4922,7 +4943,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4954,7 +4975,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5002,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5018,7 +5039,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5029,7 +5050,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5063,12 +5084,138 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } } +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_fetch(Datum containerSource, SubscriptingRefState *sbstate) +{ + return jsonb_get_element(DatumGetJsonbP(containerSource), + sbstate->upperindex, + sbstate->numupper, + &sbstate->resnull, + false); +} + + + +/* + * Perform an actual data extraction or modification for the jsonb + * subscripting. As a result the extracted Datum or the modified containers + * value will be returned. + */ +Datum +jsonb_subscript_assign(Datum containerSource, SubscriptingRefState *sbstate) +{ + /* + * the original jsonb must be non-NULL, else we punt and return the + * original array. + */ + if (sbstate->resnull) + return containerSource; + + return jsonb_set_element(containerSource, + sbstate->upperindex, + sbstate->numupper, + sbstate->replacevalue, + sbstate->refelemtype, + sbstate->replacenull); +} + +/* + * Perform preparation for the jsonb subscripting. Since there are not any + * particular restrictions for this kind of subscripting, we will verify that + * it is not a slice operation. This function produces an expression that + * represents the result of extracting a single container element or the new + * container value with the source data inserted into the right part of the + * container. If you have read until this point, and will submit a meaningful + * review of this patch series, I'll owe you a beer at the next PGConfEU. + */ + +/* + * Handle jsonb-type subscripting logic. + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + SubscriptRoutines *sbsroutines = (SubscriptRoutines *) + palloc(sizeof(SubscriptRoutines)); + + sbsroutines->prepare = jsonb_subscript_prepare; + sbsroutines->validate = jsonb_subscript_validate; + sbsroutines->fetch = jsonb_subscript_fetch; + sbsroutines->assign = jsonb_subscript_assign; + + PG_RETURN_POINTER(sbsroutines); +} + +SubscriptingRef * +jsonb_subscript_prepare(bool isAssignment, SubscriptingRef *sbsref) +{ + if (isAssignment) + { + sbsref->refelemtype = exprType((Node *) sbsref->refassgnexpr); + sbsref->refassgntype = exprType((Node *) sbsref->refassgnexpr); + } + else + sbsref->refelemtype = JSONBOID; + + return sbsref; +} + +SubscriptingRef * +jsonb_subscript_validate(bool isAssignment, SubscriptingRef *sbsref, + ParseState *pstate) +{ + List *upperIndexpr = NIL; + ListCell *l; + + if (sbsref->reflowerindexpr != NIL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->reflowerindexpr)))))); + + foreach(l, sbsref->refupperindexpr) + { + Node *subexpr = (Node *) lfirst(l); + + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation( + ((Node *) linitial(sbsref->refupperindexpr)))))); + + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + sbsref->refupperindexpr = upperIndexpr; + + return sbsref; +} + /* * Parse information about what elements of a jsonb document we want to iterate * in functions iterate_json(b)_values. This information is presented in jsonb diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 2c6aa65bf8..abcbf97d05 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10898,6 +10898,14 @@ proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float8_pass_by_value,data_page_checksum_version}', prosrc => 'pg_control_init' }, +# type subscripting support +{ oid => '6098', + descr => 'Jsonb subscripting logic', + proname => 'jsonb_subscript_handler', + prorettype => 'internal', + proargtypes => 'internal', + prosrc => 'jsonb_subscript_handler' }, + { oid => '6099', descr => 'Array subscripting logic', proname => 'array_subscript_handler', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 21489a02ae..fa7e1d22a5 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -456,7 +456,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubshandler => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..6e3b75d56a 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,6 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); +extern JsonbValue *to_jsonb_worker(Datum source, Oid source_type, bool is_null); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..04a146a7d0 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,237 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +ERROR: subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..12541e7e50 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,72 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = 1 where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = 1 where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = 'test'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = 1; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --j77abfbqdsj2lq6d Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v34-0004-Subscripting-documentation.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v39] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 412 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 981 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index ce09ad7375..0ef0f36e36 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..b91a140494 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,412 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 12557ce3af..1925cd8026 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4153,58 +4201,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4476,7 +4472,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4634,7 +4631,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4792,10 +4790,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4848,11 +4846,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4869,7 +4867,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4900,7 +4898,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4923,7 +4921,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4955,7 +4953,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5003,7 +5001,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5019,7 +5017,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5030,7 +5028,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5064,7 +5062,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index e6c7b070f6..82570cce6f 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10943,6 +10943,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 28240bdce3..3c0ee2a81b 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..eefe5d55ee 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..5b8a51f712 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --65dnqzlcwvdscbys-- ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v38] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb of type object and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 +++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 +++++++- src/backend/utils/adt/jsonbsubs.c | 282 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 +++++++++--------- src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 273 ++++++++++++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 ++++++++- 10 files changed, 852 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..cad7b02559 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is {"1": 1} +UPDATE table_name SET jsonb_field[1] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index ce09ad7375..0ef0f36e36 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..b58efb7c0d --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,282 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subexpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + subexpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subexpr = coerce_to_target_type(pstate, + subexpr, exprType(subexpr), + TEXTOID, -1, + COERCION_ASSIGNMENT, + COERCE_IMPLICIT_CAST, + -1); + if (subexpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subexpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subexpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb of object + * type and proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 12557ce3af..1925cd8026 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4153,58 +4201,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4476,7 +4472,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4634,7 +4631,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4792,10 +4790,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4848,11 +4846,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4869,7 +4867,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4900,7 +4898,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4923,7 +4921,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4955,7 +4953,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -5003,7 +5001,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5019,7 +5017,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5030,7 +5028,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5064,7 +5062,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index e6c7b070f6..82570cce6f 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10943,6 +10943,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 28240bdce3..3c0ee2a81b 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index a70cd0b7c1..85f8364d70 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4567,7 +4567,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4697,6 +4697,277 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"0": 1} +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index 3e2b8f66df..5b8a51f712 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1172,7 +1172,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1203,6 +1203,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --hletpuqfhzttgv77-- ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v40 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --byo64sf23gz7hdj6 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v40-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v45 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2v7pubbjx3p2om6u Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v45-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v43 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --6snw7vcvuujiswgu Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v43-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v46 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --mygb4tp4jvuwryfl Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v46-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v42 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --2lozexjxkmbehzdg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v42-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v41 1/2] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --bnxkghd4qzx6dtmd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v41-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v44 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule --- doc/src/sgml/json.sgml | 48 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 982 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..100d1a60f4 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,54 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + <type>jsonb</type> data type supports array-style subscripting expressions + to extract or update particular elements. It's possible to use multiple + subscripting expressions to extract nested values. In this case, a chain of + subscripting expressions follows the same rules as the + <literal>path</literal> argument in <literal>jsonb_set</literal> function, + e.g. in case of arrays it is a 0-based operation or that negative integers + that appear in <literal>path</literal> count from the end of JSON arrays. + The result of subscripting expressions is always jsonb data type. An + example of subscripting syntax: +<programlisting> +-- Extract value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update value by key, note the single quotes - the assigned value +-- needs to be of jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Select records using where clause with subscripting. Since the result of +-- subscripting is jsonb and we basically want to compare two jsonb objects, we +-- need to put the value in double quotes to be able to convert it to jsonb. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + Subscripting for <type>jsonb</type> does not support slice expressions, + even if it contains an array. + + In case if source <type>jsonb</type> is <literal>NULL</literal>, assignment + via subscripting will proceed as if it was an empty JSON object: +<programlisting> +-- If jsonb_field here is NULL, the result is {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- If jsonb_field here is NULL, the result is [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..306c37b5a6 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coercet to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..bb3f25ec3f 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coercet to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --i5uwshohlpbxyckd Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v44-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v48 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --m4t3wpskod5t4yye Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v48-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* [PATCH v49 1/3] Subscripting for jsonb @ 2020-12-18 16:19 Dmitrii Dolgov <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Dmitrii Dolgov @ 2020-12-18 16:19 UTC (permalink / raw) Subscripting implementation for jsonb. It does not support slices, does not have a limit for number of subscripts and for assignment expects a replace value to be of jsonb type. There is also one functional difference in assignment via subscripting from jsonb_set, when an original jsonb container is NULL, subscripting replaces it with an empty jsonb and proceed with assignment. For the sake of code reuse, some parts of jsonb functionality were rearranged to allow use the same functions for jsonb_set and assign subscripting operation. The original idea belongs to Oleg Bartunov. Reviewed-by: Tom Lane, Arthur Zakirov, Pavel Stehule, Dian M Fay --- doc/src/sgml/json.sgml | 51 ++++ src/backend/utils/adt/Makefile | 1 + src/backend/utils/adt/jsonb_util.c | 76 ++++- src/backend/utils/adt/jsonbsubs.c | 413 ++++++++++++++++++++++++++++ src/backend/utils/adt/jsonfuncs.c | 180 ++++++------ src/include/catalog/pg_proc.dat | 4 + src/include/catalog/pg_type.dat | 3 +- src/include/utils/jsonb.h | 6 +- src/test/regress/expected/jsonb.out | 272 +++++++++++++++++- src/test/regress/sql/jsonb.sql | 84 +++++- 10 files changed, 985 insertions(+), 105 deletions(-) create mode 100644 src/backend/utils/adt/jsonbsubs.c diff --git a/doc/src/sgml/json.sgml b/doc/src/sgml/json.sgml index 5b9a5557a4..3ace5e444b 100644 --- a/doc/src/sgml/json.sgml +++ b/doc/src/sgml/json.sgml @@ -602,6 +602,57 @@ SELECT jdoc->'guid', jdoc->'name' FROM api WHERE jdoc @> '{"tags": ["qu </para> </sect2> + <sect2 id="jsonb-subscripting"> + <title><type>jsonb</type> Subscripting</title> + <para> + The <type>jsonb</type> data type supports array-style subscripting expressions + to extract and modify elements. Nested values can be indicated by chaining + subscripting expressions, following the same rules as the <literal>path</literal> + argument in the <literal>jsonb_set</literal> function. If a <type>jsonb</type> + value is an array, numeric subscripts start at zero, and negative integers count + backwards from the last element of the array. Slice expressions are not supported. + The result of a subscripting expression is always of the jsonb data type. + </para> + + <para> + An example of subscripting syntax: +<programlisting> + +-- Extract object value by key +SELECT ('{"a": 1}'::jsonb)['a']; + +-- Extract nested object value by key path +SELECT ('{"a": {"b": {"c": 1}}}'::jsonb)['a']['b']['c']; + +-- Extract array element by index +SELECT ('[1, "2", null]'::jsonb)[1]; + +-- Update object value by key. Note the quotes around '1': the assigned +-- value must be of the jsonb type as well +UPDATE table_name SET jsonb_field['key'] = '1'; + +-- Filter records using a WHERE clause with subscripting. Since the result of +-- subscripting is jsonb, the value we compare it against must also be jsonb. +-- The double quotes make "value" also a valid jsonb string. +SELECT * FROM table_name WHERE jsonb_field['key'] = '"value"'; +</programlisting> + + <type>jsonb</type> assignment via subscripting handles a few edge cases + differently from <literal>jsonb_set</literal>. When a source <type>jsonb</type> + is <literal>NULL</literal>, assignment via subscripting will proceed as if + it was an empty JSON object: + +<programlisting> +-- Where jsonb_field was NULL, it is now {"a": 1} +UPDATE table_name SET jsonb_field['a'] = '1'; + +-- Where jsonb_field was NULL, it is now [1] +UPDATE table_name SET jsonb_field[0] = '1'; +</programlisting> + + </para> + </sect2> + <sect2> <title>Transforms</title> diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 82732146d3..279ff15ade 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -50,6 +50,7 @@ OBJS = \ jsonb_op.o \ jsonb_util.o \ jsonfuncs.o \ + jsonbsubs.o \ jsonpath.o \ jsonpath_exec.o \ jsonpath_gram.o \ diff --git a/src/backend/utils/adt/jsonb_util.c b/src/backend/utils/adt/jsonb_util.c index 4eeffa1424..41a1c1f9bb 100644 --- a/src/backend/utils/adt/jsonb_util.c +++ b/src/backend/utils/adt/jsonb_util.c @@ -68,18 +68,29 @@ static JsonbValue *pushJsonbValueScalar(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *scalarVal); +JsonbValue * +JsonbToJsonbValue(Jsonb *jsonb) +{ + JsonbValue *val = (JsonbValue *) palloc(sizeof(JsonbValue)); + + val->type = jbvBinary; + val->val.binary.data = &jsonb->root; + val->val.binary.len = VARSIZE(jsonb) - VARHDRSZ; + + return val; +} + /* * Turn an in-memory JsonbValue into a Jsonb for on-disk storage. * - * There isn't a JsonbToJsonbValue(), because generally we find it more - * convenient to directly iterate through the Jsonb representation and only - * really convert nested scalar values. JsonbIteratorNext() does this, so that - * clients of the iteration code don't have to directly deal with the binary - * representation (JsonbDeepContains() is a notable exception, although all - * exceptions are internal to this module). In general, functions that accept - * a JsonbValue argument are concerned with the manipulation of scalar values, - * or simple containers of scalar values, where it would be inconvenient to - * deal with a great amount of other state. + * Generally we find it more convenient to directly iterate through the Jsonb + * representation and only really convert nested scalar values. + * JsonbIteratorNext() does this, so that clients of the iteration code don't + * have to directly deal with the binary representation (JsonbDeepContains() is + * a notable exception, although all exceptions are internal to this module). + * In general, functions that accept a JsonbValue argument are concerned with + * the manipulation of scalar values, or simple containers of scalar values, + * where it would be inconvenient to deal with a great amount of other state. */ Jsonb * JsonbValueToJsonb(JsonbValue *val) @@ -563,6 +574,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, JsonbValue *res = NULL; JsonbValue v; JsonbIteratorToken tok; + int i; + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvObject) + { + pushJsonbValue(pstate, WJB_BEGIN_OBJECT, NULL); + for (i = 0; i < jbval->val.object.nPairs; i++) + { + pushJsonbValue(pstate, WJB_KEY, &jbval->val.object.pairs[i].key); + pushJsonbValue(pstate, WJB_VALUE, &jbval->val.object.pairs[i].value); + } + + return pushJsonbValue(pstate, WJB_END_OBJECT, NULL); + } + + if (jbval && (seq == WJB_ELEM || seq == WJB_VALUE) && jbval->type == jbvArray) + { + pushJsonbValue(pstate, WJB_BEGIN_ARRAY, NULL); + for (i = 0; i < jbval->val.array.nElems; i++) + { + pushJsonbValue(pstate, WJB_ELEM, &jbval->val.array.elems[i]); + } + + return pushJsonbValue(pstate, WJB_END_ARRAY, NULL); + } if (!jbval || (seq != WJB_ELEM && seq != WJB_VALUE) || jbval->type != jbvBinary) @@ -573,9 +608,30 @@ pushJsonbValue(JsonbParseState **pstate, JsonbIteratorToken seq, /* unpack the binary and add each piece to the pstate */ it = JsonbIteratorInit(jbval->val.binary.data); + + if ((jbval->val.binary.data->header & JB_FSCALAR) && *pstate) + { + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_BEGIN_ARRAY); + Assert(v.type == jbvArray && v.val.array.rawScalar); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_ELEM); + + res = pushJsonbValueScalar(pstate, seq, &v); + + tok = JsonbIteratorNext(&it, &v, true); + Assert(tok == WJB_END_ARRAY); + Assert(it == NULL); + + return res; + } + while ((tok = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) res = pushJsonbValueScalar(pstate, tok, - tok < WJB_BEGIN_ARRAY ? &v : NULL); + tok < WJB_BEGIN_ARRAY || + (tok == WJB_BEGIN_ARRAY && + v.val.array.rawScalar) ? &v : NULL); return res; } diff --git a/src/backend/utils/adt/jsonbsubs.c b/src/backend/utils/adt/jsonbsubs.c new file mode 100644 index 0000000000..5237414be4 --- /dev/null +++ b/src/backend/utils/adt/jsonbsubs.c @@ -0,0 +1,413 @@ +/*------------------------------------------------------------------------- + * + * jsonbsubs.c + * Subscripting support functions for jsonb. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/adt/jsonbsubs.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "executor/execExpr.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "nodes/subscripting.h" +#include "parser/parse_coerce.h" +#include "parser/parse_expr.h" +#include "utils/jsonb.h" +#include "utils/jsonfuncs.h" +#include "utils/builtins.h" +#include "utils/lsyscache.h" + + +/* SubscriptingRefState.workspace for jsonb subscripting execution */ +typedef struct JsonbSubWorkspace +{ + bool expectArray; /* jsonb root is expected to be an array */ + Oid *indexOid; /* OID of coerced subscript expression, + could be only integer or text */ + Datum *index; /* Subscript values in Datum format */ +} JsonbSubWorkspace; + + +/* + * Finish parse analysis of a SubscriptingRef expression for a jsonb. + * + * Transform the subscript expressions, coerce them to text, + * and determine the result type of the SubscriptingRef node. + */ +static void +jsonb_subscript_transform(SubscriptingRef *sbsref, + List *indirection, + ParseState *pstate, + bool isSlice, + bool isAssignment) +{ + List *upperIndexpr = NIL; + ListCell *idx; + + /* + * Transform and convert the subscript expressions. Jsonb subscripting does + * not support slices, look only and the upper index. + */ + foreach(idx, indirection) + { + A_Indices *ai = lfirst_node(A_Indices, idx); + Node *subExpr; + + if (isSlice) + { + Node *expr = ai->uidx ? ai->uidx : ai->lidx; + + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(expr)))); + } + + if (ai->uidx) + { + Oid subExprType = InvalidOid, + targetType = UNKNOWNOID; + + subExpr = transformExpr(pstate, ai->uidx, pstate->p_expr_kind); + subExprType = exprType(subExpr); + + if (subExprType != UNKNOWNOID) + { + Oid targets[2] = {INT4OID, TEXTOID}; + + /* + * Jsonb can handle multiple subscript types, but cases when a + * subscript could be coerced to multiple target types must be + * avoided, similar to overloaded functions. It could be + * possibly extend with jsonpath in the future. + */ + for (int i = 0; i < 2; i++) + { + if (can_coerce_type(1, &subExprType, &targets[i], COERCION_IMPLICIT)) + { + /* + * One type has already succeeded, it means there are + * two coercion targets possible, failure. + */ + if (targetType != UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced " + "only to one type, integer or text."), + parser_errposition(pstate, exprLocation(subExpr)))); + + targetType = targets[i]; + } + } + + /* + * No suitable types were found, failure. + */ + if (targetType == UNKNOWNOID) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("subscript type is not supported"), + errhint("Jsonb subscript must be coerced to either integer or text"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + targetType = TEXTOID; + + /* + * We known from can_coerce_type that coercion will succeed, so + * coerce_type could be used. Note the implicit coercion context, + * which is required to handle subscripts of different types, + * similar to overloaded functions. + */ + subExpr = coerce_type(pstate, + subExpr, subExprType, + targetType, -1, + COERCION_IMPLICIT, + COERCE_IMPLICIT_CAST, + -1); + if (subExpr == NULL) + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript must have text type"), + parser_errposition(pstate, exprLocation(subExpr)))); + } + else + { + /* + * Slice with omitted upper bound. Should not happen as we already + * errored out on slice earlier, but handle this just in case. + */ + Assert(isSlice && ai->is_slice); + ereport(ERROR, + (errcode(ERRCODE_DATATYPE_MISMATCH), + errmsg("jsonb subscript does not support slices"), + parser_errposition(pstate, exprLocation(ai->uidx)))); + } + + upperIndexpr = lappend(upperIndexpr, subExpr); + } + + /* store the transformed lists into the SubscriptRef node */ + sbsref->refupperindexpr = upperIndexpr; + sbsref->reflowerindexpr = NIL; + + /* Determine the result type of the subscripting operation; always jsonb */ + sbsref->refrestype = JSONBOID; + sbsref->reftypmod = -1; +} + +/* + * During execution, process the subscripts in a SubscriptingRef expression. + * + * The subscript expressions are already evaluated in Datum form in the + * SubscriptingRefState's arrays. Check and convert them as necessary. + * + * If any subscript is NULL, we throw error in assignment cases, or in fetch + * cases set result to NULL and return false (instructing caller to skip the + * rest of the SubscriptingRef sequence). + */ +static bool +jsonb_subscript_check_subscripts(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref_subscript.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + + /* + * In case if the first subscript is an integer, the source jsonb is + * expected to be an array. This information is not used directly, all such + * cases are handled within corresponding jsonb assign functions. But if + * the source jsonb is NULL the expected type will be used to construct an + * empty source. + */ + if (sbsrefstate->numupper > 0 && sbsrefstate->upperprovided[0] && + !sbsrefstate->upperindexnull[0] && workspace->indexOid[0] == INT4OID) + workspace->expectArray = true; + + /* Process upper subscripts */ + for (int i = 0; i < sbsrefstate->numupper; i++) + { + if (sbsrefstate->upperprovided[i]) + { + /* If any index expr yields NULL, result is NULL or error */ + if (sbsrefstate->upperindexnull[i]) + { + if (sbsrefstate->isassignment) + ereport(ERROR, + (errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED), + errmsg("jsonb subscript in assignment must not be null"))); + *op->resnull = true; + return false; + } + + /* + * For jsonb fetch and assign functions we need to provide path in + * text format. Convert if it's not already text. + */ + if (workspace->indexOid[i] == INT4OID) + { + Datum datum = sbsrefstate->upperindex[i]; + char *cs = DatumGetCString(DirectFunctionCall1(int4out, datum)); + workspace->index[i] = CStringGetTextDatum(cs); + } + else + workspace->index[i] = sbsrefstate->upperindex[i]; + } + } + + return true; +} + +/* + * Evaluate SubscriptingRef fetch for a jsonb element. + * + * Source container is in step's result variable (it's known not NULL, since + * we set fetch_strict to true). + */ +static void +jsonb_subscript_fetch(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + + /* Should not get here if source jsonb (or any subscript) is null */ + Assert(!(*op->resnull)); + + jsonbSource = DatumGetJsonbP(*op->resvalue); + *op->resvalue = jsonb_get_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + op->resnull, + false); +} + +/* + * Evaluate SubscriptingRef assignment for a jsonb element assignment. + * + * Input container (possibly null) is in result area, replacement value is in + * SubscriptingRefState's replacevalue/replacenull. + */ +static void +jsonb_subscript_assign(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + JsonbSubWorkspace *workspace = (JsonbSubWorkspace *) sbsrefstate->workspace; + Jsonb *jsonbSource; + JsonbValue *replacevalue; + + if (sbsrefstate->replacenull) + { + replacevalue = (JsonbValue *) palloc(sizeof(JsonbValue)); + replacevalue->type = jbvNull; + } + else + replacevalue = + JsonbToJsonbValue(DatumGetJsonbP(sbsrefstate->replacevalue)); + + /* + * In case if the input container is null, set up an empty jsonb and + * proceed with the assignment. + */ + if (*op->resnull) + { + JsonbValue *newSource = (JsonbValue *) palloc(sizeof(JsonbValue)); + + /* + * To avoid any surprising results, set up an empty jsonb array in case + * of an array is expected (i.e. the first subscript is integer), + * otherwise jsonb object. + */ + if (workspace->expectArray) + { + newSource->type = jbvArray; + newSource->val.array.nElems = 0; + newSource->val.array.rawScalar = false; + } + else + { + newSource->type = jbvObject; + newSource->val.object.nPairs = 0; + } + + jsonbSource = JsonbValueToJsonb(newSource); + *op->resnull = false; + } + else + jsonbSource = DatumGetJsonbP(*op->resvalue); + + *op->resvalue = jsonb_set_element(jsonbSource, + workspace->index, + sbsrefstate->numupper, + replacevalue); + /* The result is never NULL, so no need to change *op->resnull */ +} + +/* + * Compute old jsonb element value for a SubscriptingRef assignment + * expression. Will only be called if the new-value subexpression + * contains SubscriptingRef or FieldStore. This is the same as the + * regular fetch case, except that we have to handle a null jsonb, + * and the value should be stored into the SubscriptingRefState's + * prevvalue/prevnull fields. + */ +static void +jsonb_subscript_fetch_old(ExprState *state, + ExprEvalStep *op, + ExprContext *econtext) +{ + SubscriptingRefState *sbsrefstate = op->d.sbsref.state; + + if (*op->resnull) + { + /* whole jsonb is null, so any element is too */ + sbsrefstate->prevvalue = (Datum) 0; + sbsrefstate->prevnull = true; + } + else + { + Jsonb *jsonbSource = DatumGetJsonbP(*op->resvalue); + sbsrefstate->prevvalue = jsonb_get_element(jsonbSource, + sbsrefstate->upperindex, + sbsrefstate->numupper, + &sbsrefstate->prevnull, + false); + } +} + +/* + * Set up execution state for a jsonb subscript operation. Opposite to the + * arrays subscription, there is no limit for number of subscripts as jsonb + * type itself doesn't have nesting limits. + */ +static void +jsonb_exec_setup(const SubscriptingRef *sbsref, + SubscriptingRefState *sbsrefstate, + SubscriptExecSteps *methods) +{ + JsonbSubWorkspace *workspace; + ListCell *lc; + int nupper = sbsref->refupperindexpr->length; + char *ptr; + + /* Allocate type-specific workspace with space for per-subscript data */ + workspace = palloc0(MAXALIGN(sizeof(JsonbSubWorkspace)) + + nupper * (sizeof(Datum) + sizeof(Oid))); + workspace->expectArray = false; + ptr = ((char *) workspace) + MAXALIGN(sizeof(JsonbSubWorkspace)); + workspace->indexOid = (Oid *) ptr; + ptr += nupper * sizeof(Oid); + workspace->index = (Datum *) ptr; + + sbsrefstate->workspace = workspace; + + /* Collect subscript data types necessary at execution time */ + foreach(lc, sbsref->refupperindexpr) + { + Node *expr = lfirst(lc); + int i = foreach_current_index(lc); + + workspace->indexOid[i] = exprType(expr); + } + + /* + * Pass back pointers to appropriate step execution functions. + */ + methods->sbs_check_subscripts = jsonb_subscript_check_subscripts; + methods->sbs_fetch = jsonb_subscript_fetch; + methods->sbs_assign = jsonb_subscript_assign; + methods->sbs_fetch_old = jsonb_subscript_fetch_old; +} + +/* + * jsonb_subscript_handler + * Subscripting handler for jsonb. + * + */ +Datum +jsonb_subscript_handler(PG_FUNCTION_ARGS) +{ + static const SubscriptRoutines sbsroutines = { + .transform = jsonb_subscript_transform, + .exec_setup = jsonb_exec_setup, + .fetch_strict = true, /* fetch returns NULL for NULL inputs */ + .fetch_leakproof = true, /* fetch returns NULL for bad subscript */ + .store_leakproof = false /* ... but assignment throws error */ + }; + + PG_RETURN_POINTER(&sbsroutines); +} diff --git a/src/backend/utils/adt/jsonfuncs.c b/src/backend/utils/adt/jsonfuncs.c index 69100feab7..5a0ba6b220 100644 --- a/src/backend/utils/adt/jsonfuncs.c +++ b/src/backend/utils/adt/jsonfuncs.c @@ -461,18 +461,18 @@ static Datum populate_domain(DomainIOData *io, Oid typid, const char *colname, /* functions supporting jsonb_delete, jsonb_set and jsonb_concat */ static JsonbValue *IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, JsonbParseState **state); -static JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, +extern JsonbValue *setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, + JsonbParseState **st, int level, JsonbValue *newval, int op_type); static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type); + JsonbValue *newval, uint32 npairs, int op_type); static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, - int level, Jsonb *newval, uint32 nelems, int op_type); -static void addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb); + int level, + JsonbValue *newval, uint32 nelems, int op_type); /* function supporting iterate_json_values */ static void iterate_values_scalar(void *state, char *token, JsonTokenType tokentype); @@ -1448,13 +1448,9 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); Datum *pathtext; bool *pathnulls; + bool isnull; int npath; - int i; - bool have_object = false, - have_array = false; - JsonbValue *jbvp = NULL; - JsonbValue jbvbuf; - JsonbContainer *container; + Datum res; /* * If the array contains any null elements, return NULL, on the grounds @@ -1469,9 +1465,26 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) deconstruct_array(path, TEXTOID, -1, false, TYPALIGN_INT, &pathtext, &pathnulls, &npath); - /* Identify whether we have object, array, or scalar at top-level */ - container = &jb->root; + res = jsonb_get_element(jb, pathtext, npath, &isnull, as_text); + if (isnull) + PG_RETURN_NULL(); + else + PG_RETURN_DATUM(res); +} + +Datum +jsonb_get_element(Jsonb *jb, Datum *path, int npath, bool *isnull, bool as_text) +{ + JsonbContainer *container = &jb->root; + JsonbValue *jbvp = NULL; + int i; + bool have_object = false, + have_array = false; + + *isnull = false; + + /* Identify whether we have object, array, or scalar at top-level */ if (JB_ROOT_IS_OBJECT(jb)) have_object = true; else if (JB_ROOT_IS_ARRAY(jb) && !JB_ROOT_IS_SCALAR(jb)) @@ -1496,7 +1509,7 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) { if (as_text) { - PG_RETURN_TEXT_P(cstring_to_text(JsonbToCString(NULL, + return PointerGetDatum(cstring_to_text(JsonbToCString(NULL, container, VARSIZE(jb)))); } @@ -1512,22 +1525,25 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (have_object) { jbvp = getKeyJsonValueFromContainer(container, - VARDATA(pathtext[i]), - VARSIZE(pathtext[i]) - VARHDRSZ, - &jbvbuf); + VARDATA(path[i]), + VARSIZE(path[i]) - VARHDRSZ, + NULL); } else if (have_array) { long lindex; uint32 index; - char *indextext = TextDatumGetCString(pathtext[i]); + char *indextext = TextDatumGetCString(path[i]); char *endptr; errno = 0; lindex = strtol(indextext, &endptr, 10); if (endptr == indextext || *endptr != '\0' || errno != 0 || lindex > INT_MAX || lindex < INT_MIN) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } if (lindex >= 0) { @@ -1545,7 +1561,10 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) nelements = JsonContainerSize(container); if (-lindex > nelements) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else index = nelements + lindex; } @@ -1555,11 +1574,15 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) else { /* scalar, extraction yields a null */ - PG_RETURN_NULL(); + *isnull = true; + return PointerGetDatum(NULL); } if (jbvp == NULL) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } else if (i == npath - 1) break; @@ -1581,9 +1604,12 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) if (as_text) { if (jbvp->type == jbvNull) - PG_RETURN_NULL(); + { + *isnull = true; + return PointerGetDatum(NULL); + } - PG_RETURN_TEXT_P(JsonbValueAsText(jbvp)); + return PointerGetDatum(JsonbValueAsText(jbvp)); } else { @@ -1594,6 +1620,28 @@ get_jsonb_path_all(FunctionCallInfo fcinfo, bool as_text) } } +Datum +jsonb_set_element(Jsonb* jb, Datum *path, int path_len, + JsonbValue *newval) +{ + JsonbValue *res; + JsonbParseState *state = NULL; + JsonbIterator *it; + bool *path_nulls = palloc0(path_len * sizeof(bool)); + + if (newval->type == jbvArray && newval->val.array.rawScalar) + *newval = newval->val.array.elems[0]; + + it = JsonbIteratorInit(&jb->root); + + res = setPath(&it, path, path_nulls, path_len, &state, 0, + newval, JB_PATH_CREATE); + + pfree(path_nulls); + + PG_RETURN_JSONB_P(JsonbValueToJsonb(res)); +} + /* * Return the text representation of the given JsonbValue. */ @@ -4151,58 +4199,6 @@ jsonb_strip_nulls(PG_FUNCTION_ARGS) PG_RETURN_POINTER(JsonbValueToJsonb(res)); } -/* - * Add values from the jsonb to the parse state. - * - * If the parse state container is an object, the jsonb is pushed as - * a value, not a key. - * - * This needs to be done using an iterator because pushJsonbValue doesn't - * like getting jbvBinary values, so we can't just push jb as a whole. - */ -static void -addJsonbToParseState(JsonbParseState **jbps, Jsonb *jb) -{ - JsonbIterator *it; - JsonbValue *o = &(*jbps)->contVal; - JsonbValue v; - JsonbIteratorToken type; - - it = JsonbIteratorInit(&jb->root); - - Assert(o->type == jbvArray || o->type == jbvObject); - - if (JB_ROOT_IS_SCALAR(jb)) - { - (void) JsonbIteratorNext(&it, &v, false); /* skip array header */ - Assert(v.type == jbvArray); - (void) JsonbIteratorNext(&it, &v, false); /* fetch scalar value */ - - switch (o->type) - { - case jbvArray: - (void) pushJsonbValue(jbps, WJB_ELEM, &v); - break; - case jbvObject: - (void) pushJsonbValue(jbps, WJB_VALUE, &v); - break; - default: - elog(ERROR, "unexpected parent of nested structure"); - } - } - else - { - while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE) - { - if (type == WJB_KEY || type == WJB_VALUE || type == WJB_ELEM) - (void) pushJsonbValue(jbps, type, &v); - else - (void) pushJsonbValue(jbps, type, NULL); - } - } - -} - /* * SQL function jsonb_pretty (jsonb) * @@ -4474,7 +4470,8 @@ jsonb_set(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool create = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4632,7 +4629,8 @@ jsonb_insert(PG_FUNCTION_ARGS) { Jsonb *in = PG_GETARG_JSONB_P(0); ArrayType *path = PG_GETARG_ARRAYTYPE_P(1); - Jsonb *newval = PG_GETARG_JSONB_P(2); + Jsonb *newjsonb = PG_GETARG_JSONB_P(2); + JsonbValue *newval = JsonbToJsonbValue(newjsonb); bool after = PG_GETARG_BOOL(3); JsonbValue *res = NULL; Datum *path_elems; @@ -4787,10 +4785,10 @@ IteratorConcat(JsonbIterator **it1, JsonbIterator **it2, * All path elements before the last must already exist * whatever bits in op_type are set, or nothing is done. */ -static JsonbValue * +JsonbValue * setPath(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, - JsonbParseState **st, int level, Jsonb *newval, int op_type) + JsonbParseState **st, int level, JsonbValue *newval, int op_type) { JsonbValue v; JsonbIteratorToken r; @@ -4843,11 +4841,11 @@ setPath(JsonbIterator **it, Datum *path_elems, static void setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 npairs, int op_type) + JsonbValue *newval, uint32 npairs, int op_type) { - JsonbValue v; int i; - JsonbValue k; + JsonbValue k, + v; bool done = false; if (level >= path_len || path_nulls[level]) @@ -4864,7 +4862,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } for (i = 0; i < npairs; i++) @@ -4895,7 +4893,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if (!(op_type & JB_PATH_DELETE)) { (void) pushJsonbValue(st, WJB_KEY, &k); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } done = true; } @@ -4918,7 +4916,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, newkey.val.string.val = VARDATA_ANY(path_elems[level]); (void) pushJsonbValue(st, WJB_KEY, &newkey); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_VALUE, newval); } (void) pushJsonbValue(st, r, &k); @@ -4950,7 +4948,7 @@ setPathObject(JsonbIterator **it, Datum *path_elems, bool *path_nulls, static void setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, int path_len, JsonbParseState **st, int level, - Jsonb *newval, uint32 nelems, int op_type) + JsonbValue *newval, uint32 nelems, int op_type) { JsonbValue v; int idx, @@ -4998,7 +4996,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (op_type & JB_PATH_CREATE_OR_INSERT)) { Assert(newval != NULL); - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5014,7 +5012,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, r = JsonbIteratorNext(it, &v, true); /* skip */ if (op_type & (JB_PATH_INSERT_BEFORE | JB_PATH_CREATE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); /* * We should keep current value only in case of @@ -5025,7 +5023,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, (void) pushJsonbValue(st, r, &v); if (op_type & (JB_PATH_INSERT_AFTER | JB_PATH_REPLACE)) - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); done = true; } @@ -5059,7 +5057,7 @@ setPathArray(JsonbIterator **it, Datum *path_elems, bool *path_nulls, if ((op_type & JB_PATH_CREATE_OR_INSERT) && !done && level == path_len - 1 && i == nelems - 1) { - addJsonbToParseState(st, newval); + (void) pushJsonbValue(st, WJB_ELEM, newval); } } } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 139f4a08bd..feae8cc4b0 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11239,6 +11239,10 @@ { oid => '9256', descr => 'raw array subscripting support', proname => 'raw_array_subscript_handler', prorettype => 'internal', proargtypes => 'internal', prosrc => 'raw_array_subscript_handler' }, +# type subscripting support +{ oid => '6098', descr => 'jsonb subscripting logic', + proname => 'jsonb_subscript_handler', prorettype => 'internal', + proargtypes => 'internal', prosrc => 'jsonb_subscript_handler' }, # collation management functions { oid => '3445', descr => 'import collations from operating system', diff --git a/src/include/catalog/pg_type.dat b/src/include/catalog/pg_type.dat index 62018f063a..4a530ca907 100644 --- a/src/include/catalog/pg_type.dat +++ b/src/include/catalog/pg_type.dat @@ -444,7 +444,8 @@ { oid => '3802', array_type_oid => '3807', descr => 'Binary JSON', typname => 'jsonb', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonb_in', typoutput => 'jsonb_out', typreceive => 'jsonb_recv', - typsend => 'jsonb_send', typalign => 'i', typstorage => 'x' }, + typsend => 'jsonb_send', typalign => 'i', typstorage => 'x', + typsubscript => 'jsonb_subscript_handler' }, { oid => '4072', array_type_oid => '4073', descr => 'JSON path', typname => 'jsonpath', typlen => '-1', typbyval => 'f', typcategory => 'U', typinput => 'jsonpath_in', typoutput => 'jsonpath_out', diff --git a/src/include/utils/jsonb.h b/src/include/utils/jsonb.h index 5860011693..64f1ccbf77 100644 --- a/src/include/utils/jsonb.h +++ b/src/include/utils/jsonb.h @@ -392,6 +392,7 @@ extern JsonbValue *pushJsonbValue(JsonbParseState **pstate, extern JsonbIterator *JsonbIteratorInit(JsonbContainer *container); extern JsonbIteratorToken JsonbIteratorNext(JsonbIterator **it, JsonbValue *val, bool skipNested); +extern JsonbValue *JsonbToJsonbValue(Jsonb *jsonb); extern Jsonb *JsonbValueToJsonb(JsonbValue *val); extern bool JsonbDeepContains(JsonbIterator **val, JsonbIterator **mContained); @@ -407,5 +408,8 @@ extern char *JsonbToCStringIndent(StringInfo out, JsonbContainer *in, extern bool JsonbExtractScalar(JsonbContainer *jbc, JsonbValue *res); extern const char *JsonbTypeName(JsonbValue *jb); - +extern Datum jsonb_set_element(Jsonb *jb, Datum *path, int path_len, + JsonbValue *newval); +extern Datum jsonb_get_element(Jsonb *jb, Datum *path, int npath, + bool *isnull, bool as_text); #endif /* __JSONB_H__ */ diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out index 1e6c6ef200..46bf2e2353 100644 --- a/src/test/regress/expected/jsonb.out +++ b/src/test/regress/expected/jsonb.out @@ -4599,7 +4599,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_ {"a": 1, "b": null} (1 row) -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); jsonb_insert @@ -4729,6 +4729,276 @@ HINT: Try using the function jsonb_set to replace key value. select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); ERROR: cannot replace existing key HINT: Try using the function jsonb_set to replace key value. +-- jsonb subscript +select ('123'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('123'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['a']; + jsonb +------- + 1 +(1 row) + +select ('{"a": 1}'::jsonb)[0]; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)['not_exist']; + jsonb +------- + +(1 row) + +select ('{"a": 1}'::jsonb)[NULL]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[0]; + jsonb +------- + 1 +(1 row) + +select ('[1, "2", null]'::jsonb)['1']; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1.0]; +ERROR: subscript type is not supported +LINE 1: select ('[1, "2", null]'::jsonb)[1.0]; + ^ +HINT: Jsonb subscript must be coerced to either integer or text +select ('[1, "2", null]'::jsonb)[2]; + jsonb +------- + null +(1 row) + +select ('[1, "2", null]'::jsonb)[3]; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[-2]; + jsonb +------- + "2" +(1 row) + +select ('[1, "2", null]'::jsonb)[1]['a']; + jsonb +------- + +(1 row) + +select ('[1, "2", null]'::jsonb)[1][0]; + jsonb +------- + +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; + jsonb +------- + "c" +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; + jsonb +----------- + [1, 2, 3] +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; + jsonb +------- + 2 +(1 row) + +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; + jsonb +------- + +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; + jsonb +--------------- + {"a2": "aaa"} +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; + jsonb +------- + "aaa" +(1 row) + +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; + jsonb +------- + +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; + jsonb +----------------------- + ["aaa", "bbb", "ccc"] +(1 row) + +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + jsonb +------- + "ccc" +(1 row) + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +ERROR: jsonb subscript does not support slices +LINE 1: select ('{"a": 1}'::jsonb)['a':'b']; + ^ +select ('[1, "2", null]'::jsonb)[1:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:2]; + ^ +select ('[1, "2", null]'::jsonb)[:2]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[:2]; + ^ +select ('[1, "2", null]'::jsonb)[1:]; +ERROR: jsonb subscript does not support slices +LINE 1: select ('[1, "2", null]'::jsonb)[1:]; + ^ +select ('[1, "2", null]'::jsonb)[:]; +ERROR: jsonb subscript does not support slices +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + id | test_json +----+------------------ + 2 | {"key": "value"} + 1 | {"a": 1} +(2 rows) + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + id | test_json +----+-------------------------- + 1 | {"a": 1} + 2 | {"a": 1, "key": "value"} +(2 rows) + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------- + 1 | {"a": "test"} + 2 | {"a": "test", "key": "value"} +(2 rows) + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------- + 1 | {"a": {"b": 1}} + 2 | {"a": {"b": 1}, "key": "value"} +(2 rows) + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + id | test_json +----+---------------------------------- + 1 | {"a": [1, 2, 3]} + 2 | {"a": [1, 2, 3], "key": "value"} +(2 rows) + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; + id | test_json +----+---------------------------------- + 2 | {"a": [1, 2, 3], "key": "value"} +(1 row) + +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; + id | test_json +----+----------- +(0 rows) + +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + id | test_json +----+----------- +(0 rows) + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +ERROR: jsonb subscript in assignment must not be null +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} +(2 rows) + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + id | test_json +----+------------------------------------------------------- + 1 | {"a": [1, 2, 3], "another_key": null} + 2 | {"a": [1, 2, 3], "key": "value", "another_key": null} + 3 | {"a": 1} +(3 rows) + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + id | test_json +----+--------------------------------------------------------------- + 1 | {"0": 1, "a": [1, 2, 3], "another_key": null} + 2 | {"0": 1, "a": [1, 2, 3], "key": "value", "another_key": null} + 3 | [1] +(3 rows) + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); to_tsvector diff --git a/src/test/regress/sql/jsonb.sql b/src/test/regress/sql/jsonb.sql index b6409767f6..20aa8fe0e2 100644 --- a/src/test/regress/sql/jsonb.sql +++ b/src/test/regress/sql/jsonb.sql @@ -1177,7 +1177,7 @@ select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'retu select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'delete_key') as delete_key; select jsonb_set_lax('{"a":1,"b":2}', '{b}', null, null_value_treatment => 'use_json_null') as use_json_null; -\pset null +\pset null '' -- jsonb_insert select jsonb_insert('{"a": [0,1,2]}', '{a, 1}', '"new_value"'); @@ -1208,6 +1208,88 @@ select jsonb_insert('{"a": {"b": "value"}}', '{a, c}', '"new_value"', true); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"'); select jsonb_insert('{"a": {"b": "value"}}', '{a, b}', '"new_value"', true); +-- jsonb subscript +select ('123'::jsonb)['a']; +select ('123'::jsonb)[0]; +select ('123'::jsonb)[NULL]; +select ('{"a": 1}'::jsonb)['a']; +select ('{"a": 1}'::jsonb)[0]; +select ('{"a": 1}'::jsonb)['not_exist']; +select ('{"a": 1}'::jsonb)[NULL]; +select ('[1, "2", null]'::jsonb)['a']; +select ('[1, "2", null]'::jsonb)[0]; +select ('[1, "2", null]'::jsonb)['1']; +select ('[1, "2", null]'::jsonb)[1.0]; +select ('[1, "2", null]'::jsonb)[2]; +select ('[1, "2", null]'::jsonb)[3]; +select ('[1, "2", null]'::jsonb)[-2]; +select ('[1, "2", null]'::jsonb)[1]['a']; +select ('[1, "2", null]'::jsonb)[1][0]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['b']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d'][1]; +select ('{"a": 1, "b": "c", "d": [1, 2, 3]}'::jsonb)['d']['a']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']; +select ('{"a": {"a1": {"a2": "aaa"}}, "b": "bbb", "c": "ccc"}'::jsonb)['a']['a1']['a2']['a3']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1']; +select ('{"a": ["a1", {"b1": ["aaa", "bbb", "ccc"]}], "b": "bb"}'::jsonb)['a'][1]['b1'][2]; + +-- slices are not supported +select ('{"a": 1}'::jsonb)['a':'b']; +select ('[1, "2", null]'::jsonb)[1:2]; +select ('[1, "2", null]'::jsonb)[:2]; +select ('[1, "2", null]'::jsonb)[1:]; +select ('[1, "2", null]'::jsonb)[:]; + +create TEMP TABLE test_jsonb_subscript ( + id int, + test_json jsonb +); + +insert into test_jsonb_subscript values +(1, '{}'), -- empty jsonb +(2, '{"key": "value"}'); -- jsonb with data + +-- update empty jsonb +update test_jsonb_subscript set test_json['a'] = '1' where id = 1; +select * from test_jsonb_subscript; + +-- update jsonb with some data +update test_jsonb_subscript set test_json['a'] = '1' where id = 2; +select * from test_jsonb_subscript; + +-- replace jsonb +update test_jsonb_subscript set test_json['a'] = '"test"'; +select * from test_jsonb_subscript; + +-- replace by object +update test_jsonb_subscript set test_json['a'] = '{"b": 1}'::jsonb; +select * from test_jsonb_subscript; + +-- replace by array +update test_jsonb_subscript set test_json['a'] = '[1, 2, 3]'::jsonb; +select * from test_jsonb_subscript; + +-- use jsonb subscription in where clause +select * from test_jsonb_subscript where test_json['key'] = '"value"'; +select * from test_jsonb_subscript where test_json['key_doesnt_exists'] = '"value"'; +select * from test_jsonb_subscript where test_json['key'] = '"wrong_value"'; + +-- NULL +update test_jsonb_subscript set test_json[NULL] = '1'; +update test_jsonb_subscript set test_json['another_key'] = NULL; +select * from test_jsonb_subscript; + +-- NULL as jsonb source +insert into test_jsonb_subscript values (3, NULL); +update test_jsonb_subscript set test_json['a'] = '1' where id = 3; +select * from test_jsonb_subscript; + +update test_jsonb_subscript set test_json = NULL where id = 3; +update test_jsonb_subscript set test_json[0] = '1'; +select * from test_jsonb_subscript; + -- jsonb to tsvector select to_tsvector('{"a": "aaa bbb ddd ccc", "b": ["eee fff ggg"], "c": {"d": "hhh iii"}}'::jsonb); -- 2.21.0 --3x42k255okwqcjpg Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v49-0002-Filling-gaps-in-jsonb.patch" ^ permalink raw reply [nested|flat] 203+ messages in thread
* Re: refactoring basebackup.c @ 2022-01-19 12:16 Dipesh Pandit <[email protected]> 2022-01-19 15:56 ` Re: refactoring basebackup.c Robert Haas <[email protected]> 2022-01-19 21:26 ` Re: refactoring basebackup.c Robert Haas <[email protected]> 0 siblings, 2 replies; 203+ messages in thread From: Dipesh Pandit @ 2022-01-19 12:16 UTC (permalink / raw) To: Robert Haas <[email protected]>; +Cc: Jeevan Ladhe <[email protected]>; tushar <[email protected]>; Dmitry Dolgov <[email protected]>; Mark Dilger <[email protected]>; pgsql-hackers Hi, I have added support for decompressing a gzip compressed tar file at client. pg_basebackup can enable server side compression for plain format backup with this change. Added a gzip extractor which decompresses the compressed archive and forwards it to the next streamer. I have done initial testing and working on updating the test coverage. Note: Before applying the patch, please apply Robert's v11 version of the patches 0001 and 0002. Thanks, Dipesh Attachments: [text/x-patch] v1-0001-Support-for-extracting-gzip-compressed-archive.patch (10.4K, ../../CAN1g5_FSqShfWKibkCrJr45hHtRCBQUUtGVEHn4wNv=YCkybtQ@mail.gmail.com/3-v1-0001-Support-for-extracting-gzip-compressed-archive.patch) download | inline diff: From 737badce26ed05b5cdb64d9ffd1735fef9acbbf8 Mon Sep 17 00:00:00 2001 From: Dipesh Pandit <[email protected]> Date: Wed, 19 Jan 2022 17:11:45 +0530 Subject: [PATCH] Support for extracting gzip compressed archive pg_basebackup can support server side compression using gzip. In order to support plain format backup with option '-Fp' we need to add support for decompressing the compressed blocks at client. This patch addresses the extraction of gzip compressed blocks at client. --- src/bin/pg_basebackup/bbstreamer.h | 1 + src/bin/pg_basebackup/bbstreamer_file.c | 175 ++++++++++++++++++++++++++++++++ src/bin/pg_basebackup/pg_basebackup.c | 58 +++++++++-- 3 files changed, 225 insertions(+), 9 deletions(-) diff --git a/src/bin/pg_basebackup/bbstreamer.h b/src/bin/pg_basebackup/bbstreamer.h index fc88b50..270b0df 100644 --- a/src/bin/pg_basebackup/bbstreamer.h +++ b/src/bin/pg_basebackup/bbstreamer.h @@ -205,6 +205,7 @@ extern bbstreamer *bbstreamer_extractor_new(const char *basepath, const char *(*link_map) (const char *), void (*report_output_file) (const char *)); +extern bbstreamer *bbstreamer_gzip_extractor_new(bbstreamer *next); extern bbstreamer *bbstreamer_tar_parser_new(bbstreamer *next); extern bbstreamer *bbstreamer_tar_terminator_new(bbstreamer *next); extern bbstreamer *bbstreamer_tar_archiver_new(bbstreamer *next); diff --git a/src/bin/pg_basebackup/bbstreamer_file.c b/src/bin/pg_basebackup/bbstreamer_file.c index 77ca222..350af1d 100644 --- a/src/bin/pg_basebackup/bbstreamer_file.c +++ b/src/bin/pg_basebackup/bbstreamer_file.c @@ -37,6 +37,13 @@ typedef struct bbstreamer_gzip_writer char *pathname; gzFile gzfile; } bbstreamer_gzip_writer; + +typedef struct bbstreamer_gzip_extractor +{ + bbstreamer base; + z_stream zstream; + size_t bytes_written; +} bbstreamer_gzip_extractor; #endif typedef struct bbstreamer_extractor @@ -76,6 +83,21 @@ const bbstreamer_ops bbstreamer_gzip_writer_ops = { .finalize = bbstreamer_gzip_writer_finalize, .free = bbstreamer_gzip_writer_free }; + +static void bbstreamer_gzip_extractor_content(bbstreamer *streamer, + bbstreamer_member *member, + const char *data, int len, + bbstreamer_archive_context context); +static void bbstreamer_gzip_extractor_finalize(bbstreamer *streamer); +static void bbstreamer_gzip_extractor_free(bbstreamer *streamer); +static void *gzip_palloc(void *opaque, unsigned items, unsigned size); +static void gzip_pfree(void *opaque, void *address); + +const bbstreamer_ops bbstreamer_gzip_extractor_ops = { + .content = bbstreamer_gzip_extractor_content, + .finalize = bbstreamer_gzip_extractor_finalize, + .free = bbstreamer_gzip_extractor_free +}; #endif static void bbstreamer_extractor_content(bbstreamer *streamer, @@ -349,6 +371,159 @@ get_gz_error(gzFile gzf) #endif /* + * Create a new base backup streamer that performs decompression of gzip + * compressed blocks. + */ +bbstreamer * +bbstreamer_gzip_extractor_new(bbstreamer *next) +{ +#ifdef HAVE_LIBZ + bbstreamer_gzip_extractor *streamer; + z_stream *zs; + + Assert(next != NULL); + + streamer = palloc0(sizeof(bbstreamer_gzip_extractor)); + *((const bbstreamer_ops **) &streamer->base.bbs_ops) = + &bbstreamer_gzip_extractor_ops; + + streamer->base.bbs_next = next; + initStringInfo(&streamer->base.bbs_buffer); + + /* Initialize internal stream state for decompression */ + zs = &streamer->zstream; + zs->zalloc = gzip_palloc; + zs->zfree = gzip_pfree; + zs->next_out = (uint8 *) streamer->base.bbs_buffer.data; + zs->avail_out = streamer->base.bbs_buffer.maxlen; + + /* + * Data compression was initialized using deflateInit2 to request a gzip + * header. Similarly, we are using inflateInit2 to initialize data + * decompression. + * "windowBits" must be greater than or equal to "windowBits" value + * provided to deflateInit2 while compressing. + */ + if (inflateInit2(zs, 15 + 16) != Z_OK) + { + pg_log_error("could not initialize compression library"); + exit(1); + + } + + return &streamer->base; +#else + pg_log_error("this build does not support compression"); + exit(1); +#endif +} + +#ifdef HAVE_LIBZ +/* + * Decompress the input data to output buffer until we ran out of the input + * data. Each time the output buffer is full invoke bbstreamer_content to pass + * on the decompressed data to next streamer. + */ +static void +bbstreamer_gzip_extractor_content(bbstreamer *streamer, + bbstreamer_member *member, + const char *data, int len, + bbstreamer_archive_context context) +{ + bbstreamer_gzip_extractor *mystreamer = (bbstreamer_gzip_extractor *) streamer; + z_stream *zs = &mystreamer->zstream; + int res; + + + zs->next_in = (uint8 *) data; + zs->avail_in = len; + + /* Process the current chunk */ + while (zs->avail_in > 0) + { + Assert(mystreamer->bytes_written < mystreamer->base.bbs_buffer.maxlen); + + zs->next_out = (uint8 *) + mystreamer->base.bbs_buffer.data + mystreamer->bytes_written; + zs->avail_out = mystreamer->base.bbs_buffer.maxlen - mystreamer->bytes_written; + + /* + * Decompresses data starting at zs->next_in and update zs->next_in + * and zs->avail_in, generate output data starting at zs->next_out + * and update zs->next_out and zs->avail_out accordingly. + */ + res = inflate(zs, Z_NO_FLUSH); + + if (res == Z_STREAM_ERROR) + pg_log_error("could not decompress data: %s", zs->msg); + + mystreamer->bytes_written = mystreamer->base.bbs_buffer.maxlen - zs->avail_out; + + /* If output buffer is full then pass on the content to next streamer */ + if (mystreamer->bytes_written >= mystreamer->base.bbs_buffer.maxlen) + { + bbstreamer_content(mystreamer->base.bbs_next, member, mystreamer->base.bbs_buffer.data, + mystreamer->base.bbs_buffer.maxlen, context); + mystreamer->bytes_written = 0; + } + } + + /* + * End of the stream, if there is some pending data in output buffers then + * we must forward it to next streamer. + */ + if (res == Z_STREAM_END) { + bbstreamer_content(mystreamer->base.bbs_next, member, mystreamer->base.bbs_buffer.data, + mystreamer->bytes_written, context); + } +} + +/* + * End-of-stream processing. + */ +static void +bbstreamer_gzip_extractor_finalize(bbstreamer *streamer) +{ + bbstreamer_gzip_extractor *mystreamer = (bbstreamer_gzip_extractor *) streamer; + + bbstreamer_finalize(mystreamer->base.bbs_next); +} + +/* + * Free memory. + */ +static void +bbstreamer_gzip_extractor_free(bbstreamer *streamer) +{ + bbstreamer_gzip_extractor *mystreamer = (bbstreamer_gzip_extractor *) streamer; + + bbstreamer_free(mystreamer->base.bbs_next); + pfree(mystreamer->base.bbs_buffer.data); + pfree(streamer); +} + +/* + * Wrapper function to adjust the signature of palloc to match what libz + * expects. + */ +static void * +gzip_palloc(void *opaque, unsigned items, unsigned size) +{ + return palloc(items * size); +} + +/* + * Wrapper function to adjust the signature of pfree to match what libz + * expects. + */ +static void +gzip_pfree(void *opaque, void *address) +{ + pfree(address); +} +#endif + +/* * Create a bbstreamer that extracts an archive. * * All pathnames in the archive are interpreted relative to basepath. diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index 6ee49a5..b5e31aa 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -111,6 +111,12 @@ typedef enum STREAM_WAL } IncludeWal; +typedef enum +{ + BACKUP_COMPRESSION_NONE, + BACKUP_COMPRESSION_GZIP +} compression_type; + /* Global options */ static char *basedir = NULL; static TablespaceList tablespace_dirs = {NULL, NULL}; @@ -173,6 +179,10 @@ static int has_xlogendptr = 0; static volatile LONG has_xlogendptr = 0; #endif +/* Server side compression method and compression level */ +static compression_type server_compression_type = BACKUP_COMPRESSION_NONE; +static int server_compression_level = 0; + /* Contents of configuration file to be generated */ static PQExpBuffer recoveryconfcontents = NULL; @@ -1028,15 +1038,23 @@ CreateBackupStreamer(char *archive_name, char *spclocation, /* At present, we only know how to parse tar archives. */ if (must_parse_archive && !is_tar) { - pg_log_error("unable to parse archive: %s", archive_name); - pg_log_info("only tar archives can be parsed"); - if (format == 'p') - pg_log_info("plain format requires pg_basebackup to parse the archive"); - if (inject_manifest) - pg_log_info("using - as the output directory requires pg_basebackup to parse the archive"); - if (writerecoveryconf) - pg_log_info("the -R option requires pg_basebackup to parse the archive"); - exit(1); + /* + * If the archived is compressed using a compression method other than + * gzip then we don't know how to extract it. + */ + if (server_compression != NULL && + server_compression_type != BACKUP_COMPRESSION_GZIP) + { + pg_log_error("unable to parse archive: %s", archive_name); + pg_log_info("only tar archives can be parsed"); + if (format == 'p') + pg_log_info("plain format requires pg_basebackup to parse the archive"); + if (inject_manifest) + pg_log_info("using - as the output directory requires pg_basebackup to parse the archive"); + if (writerecoveryconf) + pg_log_info("the -R option requires pg_basebackup to parse the archive"); + exit(1); + } } if (format == 'p') @@ -1136,6 +1154,13 @@ CreateBackupStreamer(char *archive_name, char *spclocation, else if (expect_unterminated_tarfile) streamer = bbstreamer_tar_terminator_new(streamer); + /* + * Extract the gzip compressed archive using a gzip extractor and then + * forward it to next streamer. + */ + if (format == 'p' && server_compression_type == BACKUP_COMPRESSION_GZIP) + streamer = bbstreamer_gzip_extractor_new(streamer); + /* Return the results. */ *manifest_inject_streamer_p = manifest_inject_streamer; return streamer; @@ -2448,6 +2473,21 @@ main(int argc, char **argv) exit(1); } + if (server_compression != NULL) + { + if (strcmp(server_compression, "gzip") == 0) + server_compression_type = BACKUP_COMPRESSION_GZIP; + else if (strlen(server_compression) == 5 && + strncmp(server_compression, "gzip", 4) == 0 && + server_compression[4] >= '1' && server_compression[4] <= '9') + { + server_compression_type = BACKUP_COMPRESSION_GZIP; + server_compression_level = server_compression[4] - '0'; + } + } + else + server_compression_type = BACKUP_COMPRESSION_NONE; + /* * Compression doesn't make sense unless tar format is in use. */ -- 1.8.3.1 ^ permalink raw reply [nested|flat] 203+ messages in thread
* Re: refactoring basebackup.c 2022-01-19 12:16 Re: refactoring basebackup.c Dipesh Pandit <[email protected]> @ 2022-01-19 15:56 ` Robert Haas <[email protected]> 1 sibling, 0 replies; 203+ messages in thread From: Robert Haas @ 2022-01-19 15:56 UTC (permalink / raw) To: Dipesh Pandit <[email protected]>; +Cc: Jeevan Ladhe <[email protected]>; tushar <[email protected]>; Dmitry Dolgov <[email protected]>; Mark Dilger <[email protected]>; pgsql-hackers On Wed, Jan 19, 2022 at 7:16 AM Dipesh Pandit <[email protected]> wrote: > I have added support for decompressing a gzip compressed tar file > at client. pg_basebackup can enable server side compression for > plain format backup with this change. > > Added a gzip extractor which decompresses the compressed archive > and forwards it to the next streamer. I have done initial testing and > working on updating the test coverage. Cool. It's going to need some documentation changes, too. I don't like the way you coded this in CreateBackupStreamer(). I would like the decision about whether to use bbstreamer_gzip_extractor_new(), and/or throw an error about not being able to parse an archive, to based on the file type i.e. "did we get a .tar.gz file?" rather than on whether we asked for server-side compression. Notice that the existing logic checks whether we actually got a .tar file from the server rather than assuming that's what must have happened. As a matter of style, I don't think it's good for the only thing inside of an "if" statement to be another "if" statement. The two could be merged, but we also don't want to have the "if" conditional be too complex. I am imagining that this should end up saying something like if (must_parse_archive && !is_tar && !is_tar_gz) { pg_log_error(... + * "windowBits" must be greater than or equal to "windowBits" value + * provided to deflateInit2 while compressing. It would be nice to clarify why we know the value we're using is safe. Maybe we're using the maximum possible value, in which case you could just add that to the end of the comment: "...so we use the maximum possible value for safety." + /* + * End of the stream, if there is some pending data in output buffers then + * we must forward it to next streamer. + */ + if (res == Z_STREAM_END) { + bbstreamer_content(mystreamer->base.bbs_next, member, mystreamer->base.bbs_buffer.data, + mystreamer->bytes_written, context); + } Uncuddle the brace. It probably doesn't make much difference, but I would be inclined to do the final flush in bbstreamer_gzip_extractor_finalize() rather than here. That way we rely on our own notion of when there's no more input data rather than zlib's notion. Probably terrible things are going to happen if those two ideas don't match up .... but there might be some other compression algorithm that doesn't return a distinguishing code at end-of-stream. Such an algorithm would have to take care of any leftover data in the finalize function, so I think we should do that here too, so the code can be similar in all cases. Perhaps we should move all the gzip stuff to a new file bbstreamer_gzip.c. -- Robert Haas EDB: http://www.enterprisedb.com ^ permalink raw reply [nested|flat] 203+ messages in thread
* Re: refactoring basebackup.c 2022-01-19 12:16 Re: refactoring basebackup.c Dipesh Pandit <[email protected]> @ 2022-01-19 21:26 ` Robert Haas <[email protected]> 2022-01-21 18:33 ` Re: refactoring basebackup.c Robert Haas <[email protected]> 1 sibling, 1 reply; 203+ messages in thread From: Robert Haas @ 2022-01-19 21:26 UTC (permalink / raw) To: Dipesh Pandit <[email protected]>; +Cc: Jeevan Ladhe <[email protected]>; tushar <[email protected]>; Dmitry Dolgov <[email protected]>; Mark Dilger <[email protected]>; pgsql-hackers On Wed, Jan 19, 2022 at 7:16 AM Dipesh Pandit <[email protected]> wrote: > I have done initial testing and > working on updating the test coverage. I spent some time thinking about test coverage for the server-side backup code today and came up with the attached (v12-0003). It does an end-to-end test that exercises server-side backup and server-side compression and then untars the backup and validity-checks it using pg_verifybackup. In addition to being good test coverage for these patches, it also plugs a gap in the test coverage of pg_verifybackup, which currently has no test case that untars a tar-format backup and then verifies the result. I couldn't figure out a way to do that back at the time I was working on pg_verifybackup, because I didn't think we had any existing precedent for using 'tar' from a TAP test. But it was pointed out to me that we do, so I used that as the model for this test. It should be easy to generalize this test case to test lz4 and zstd as well, I think. But I guess we'll still need something different to test what your patch is doing. -- Robert Haas EDB: http://www.enterprisedb.com Attachments: [application/octet-stream] v12-0002-Server-side-gzip-compression.patch (21.1K, ../../CA+TgmobQYkP81QQgS6tvvt4cRxvmipHQ4eU-aNjSpiZJhdkckA@mail.gmail.com/2-v12-0002-Server-side-gzip-compression.patch) download | inline diff: From 6c0f223b3c2265fe59400aa6842424bc9717f601 Mon Sep 17 00:00:00 2001 From: Robert Haas <[email protected]> Date: Fri, 5 Nov 2021 10:05:02 -0400 Subject: [PATCH v12 2/3] Server-side gzip compression. pg_basebackup now has a --server-compression option, which can be set to 'none' (the default), 'gzip', or 'gzipN' where N is a digit between 1 and 9. If set to 'gzip' or 'gzipN' it will compress the generated tar files on the server side using 'gzip', either at the default compression level or a the compression level specified by N. At present, pg_basebackup cannot decompress .gz files, so the --server-compression option will cause a failure if (1) -Ft is not used or (2) -R is used or (3) -D- is used without --no-manifest. Patch by me, with a bug fix by Jeevan Ladhe. --- doc/src/sgml/ref/pg_basebackup.sgml | 29 ++- src/backend/Makefile | 2 +- src/backend/replication/Makefile | 1 + src/backend/replication/basebackup.c | 39 +++ src/backend/replication/basebackup_gzip.c | 304 ++++++++++++++++++++++ src/bin/pg_basebackup/pg_basebackup.c | 43 ++- src/include/replication/basebackup_sink.h | 1 + 7 files changed, 415 insertions(+), 4 deletions(-) create mode 100644 src/backend/replication/basebackup_gzip.c diff --git a/doc/src/sgml/ref/pg_basebackup.sgml b/doc/src/sgml/ref/pg_basebackup.sgml index 165a9ea5cc..9ce8b8d89d 100644 --- a/doc/src/sgml/ref/pg_basebackup.sgml +++ b/doc/src/sgml/ref/pg_basebackup.sgml @@ -224,6 +224,31 @@ PostgreSQL documentation </listitem> </varlistentry> + <varlistentry> + <term><option>--server-compression=<replaceable class="parameter">target</replaceable></option></term> + <listitem> + + <para> + Allows the tar files generated for each tablespace to be compressed + on the server, before they are sent to the client. The default value + is <literal>none</literal>, which performs no compression. If set + to <literal>gzip</literal>, compression is performed using gzip and + the suffix <filename>.gz</filename> will automatically be added to + compressed files. A numeric digit between 1 and 9 can be added to + specify the compression level; for instance, <literal>gzip9</literal> + will provide the maximum compression that the <literal>gzip</literal> + algorithm can provide. + </para> + <para> + Since the write-ahead logs are fetched via a separate client + connection, they cannot be compressed using this option. See also + the <literal>--gzip</literal> and <literal>--compress</literal> + options. + </para> + + </listitem> + </varlistentry> + <varlistentry> <term><option>-t <replaceable class="parameter">target</replaceable></option></term> <term><option>--target=<replaceable class="parameter">target</replaceable></option></term> @@ -405,7 +430,9 @@ PostgreSQL documentation compression level (0 through 9, 0 being no compression and 9 being best compression). Compression is only available when using the tar format, and the suffix <filename>.gz</filename> will - automatically be added to all tar filenames. + automatically be added to all tar filenames. When this option is + used, compression is performed on the client side; + see also <literal>--server-compression</literal>. </para> </listitem> </varlistentry> diff --git a/src/backend/Makefile b/src/backend/Makefile index add9560be4..4a02006788 100644 --- a/src/backend/Makefile +++ b/src/backend/Makefile @@ -48,7 +48,7 @@ OBJS = \ LIBS := $(filter-out -lpgport -lpgcommon, $(LIBS)) $(LDAP_LIBS_BE) $(ICU_LIBS) # The backend doesn't need everything that's in LIBS, however -LIBS := $(filter-out -lz -lreadline -ledit -ltermcap -lncurses -lcurses, $(LIBS)) +LIBS := $(filter-out -lreadline -ledit -ltermcap -lncurses -lcurses, $(LIBS)) ifeq ($(with_systemd),yes) LIBS += -lsystemd diff --git a/src/backend/replication/Makefile b/src/backend/replication/Makefile index a8f4757f0c..8ec60ded76 100644 --- a/src/backend/replication/Makefile +++ b/src/backend/replication/Makefile @@ -18,6 +18,7 @@ OBJS = \ backup_manifest.o \ basebackup.o \ basebackup_copy.o \ + basebackup_gzip.o \ basebackup_progress.o \ basebackup_server.o \ basebackup_sink.o \ diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c index d32da51535..4bed0f18b7 100644 --- a/src/backend/replication/basebackup.c +++ b/src/backend/replication/basebackup.c @@ -61,6 +61,12 @@ typedef enum BACKUP_TARGET_SERVER } backup_target_type; +typedef enum +{ + BACKUP_COMPRESSION_NONE, + BACKUP_COMPRESSION_GZIP +} basebackup_compression_type; + typedef struct { const char *label; @@ -73,6 +79,8 @@ typedef struct backup_target_type target; char *target_detail; backup_manifest_option manifest; + basebackup_compression_type compression; + int compression_level; pg_checksum_type manifest_checksum_type; } basebackup_options; @@ -707,11 +715,13 @@ parse_basebackup_options(List *options, basebackup_options *opt) bool o_target = false; bool o_target_detail = false; char *target_str = "compat"; /* placate compiler */ + bool o_compression = false; MemSet(opt, 0, sizeof(*opt)); opt->target = BACKUP_TARGET_COMPAT; opt->manifest = MANIFEST_OPTION_NO; opt->manifest_checksum_type = CHECKSUM_TYPE_CRC32C; + opt->compression = BACKUP_COMPRESSION_NONE; foreach(lopt, options) { @@ -881,6 +891,31 @@ parse_basebackup_options(List *options, basebackup_options *opt) opt->target_detail = optval; o_target_detail = true; } + else if (strcmp(defel->defname, "compression") == 0) + { + char *optval = defGetString(defel); + + if (o_compression) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("duplicate option \"%s\"", defel->defname))); + if (strcmp(optval, "none") == 0) + opt->compression = BACKUP_COMPRESSION_NONE; + else if (strcmp(optval, "gzip") == 0) + opt->compression = BACKUP_COMPRESSION_GZIP; + else if (strlen(optval) == 5 && strncmp(optval, "gzip", 4) == 0 && + optval[4] >= '1' && optval[4] <= '9') + { + opt->compression = BACKUP_COMPRESSION_GZIP; + opt->compression_level = optval[4] - '0'; + } + else + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("unrecognized compression algorithm: \"%s\"", + optval))); + o_compression = true; + } } if (opt->label == NULL) opt->label = "base backup"; @@ -975,6 +1010,10 @@ SendBaseBackup(BaseBackupCmd *cmd) if (opt.maxrate > 0) sink = bbsink_throttle_new(sink, opt.maxrate); + /* Set up server-side compression, if client requested it */ + if (opt.compression == BACKUP_COMPRESSION_GZIP) + sink = bbsink_gzip_new(sink, opt.compression_level); + /* Set up progress reporting. */ sink = bbsink_progress_new(sink, opt.progress); diff --git a/src/backend/replication/basebackup_gzip.c b/src/backend/replication/basebackup_gzip.c new file mode 100644 index 0000000000..432423bd55 --- /dev/null +++ b/src/backend/replication/basebackup_gzip.c @@ -0,0 +1,304 @@ +/*------------------------------------------------------------------------- + * + * basebackup_gzip.c + * Basebackup sink implementing gzip compression. + * + * Portions Copyright (c) 2010-2020, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/backend/replication/basebackup_gzip.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#ifdef HAVE_LIBZ +#include <zlib.h> +#endif + +#include "replication/basebackup_sink.h" + +#ifdef HAVE_LIBZ +typedef struct bbsink_gzip +{ + /* Common information for all types of sink. */ + bbsink base; + + /* Compression level. */ + int compresslevel; + + /* Compressed data stream. */ + z_stream zstream; + + /* Number of bytes staged in output buffer. */ + size_t bytes_written; +} bbsink_gzip; + +static void bbsink_gzip_begin_backup(bbsink *sink); +static void bbsink_gzip_begin_archive(bbsink *sink, const char *archive_name); +static void bbsink_gzip_archive_contents(bbsink *sink, size_t len); +static void bbsink_gzip_manifest_contents(bbsink *sink, size_t len); +static void bbsink_gzip_end_archive(bbsink *sink); +static void *gzip_palloc(void *opaque, unsigned items, unsigned size); +static void gzip_pfree(void *opaque, void *address); + +const bbsink_ops bbsink_gzip_ops = { + .begin_backup = bbsink_gzip_begin_backup, + .begin_archive = bbsink_gzip_begin_archive, + .archive_contents = bbsink_gzip_archive_contents, + .end_archive = bbsink_gzip_end_archive, + .begin_manifest = bbsink_forward_begin_manifest, + .manifest_contents = bbsink_gzip_manifest_contents, + .end_manifest = bbsink_forward_end_manifest, + .end_backup = bbsink_forward_end_backup, + .cleanup = bbsink_forward_cleanup +}; +#endif + +/* + * Create a new basebackup sink that performs gzip compression using the + * designated compression level. + */ +bbsink * +bbsink_gzip_new(bbsink *next, int compresslevel) +{ +#ifndef HAVE_LIBZ + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("gzip compression is not supported by this build"))); +#else + bbsink_gzip *sink; + + Assert(next != NULL); + Assert(compresslevel >= 0 && compresslevel <= 9); + + if (compresslevel == 0) + compresslevel = Z_DEFAULT_COMPRESSION; + + sink = palloc0(sizeof(bbsink_gzip)); + *((const bbsink_ops **) &sink->base.bbs_ops) = &bbsink_gzip_ops; + sink->base.bbs_next = next; + sink->compresslevel = compresslevel; + + return &sink->base; +#endif +} + +#ifdef HAVE_LIBZ + +/* + * Begin backup. + */ +static void +bbsink_gzip_begin_backup(bbsink *sink) +{ + /* + * We need our own buffer, because we're going to pass different data to + * the next sink than what gets passed to us. + */ + sink->bbs_buffer = palloc(sink->bbs_buffer_length); + + /* + * Since deflate() doesn't require the output buffer to be of any + * particular size, we can just make it the same size as the input buffer. + */ + bbsink_begin_backup(sink->bbs_next, sink->bbs_state, + sink->bbs_buffer_length); +} + +/* + * Prepare to compress the next archive. + */ +static void +bbsink_gzip_begin_archive(bbsink *sink, const char *archive_name) +{ + bbsink_gzip *mysink = (bbsink_gzip *) sink; + char *gz_archive_name; + z_stream *zs = &mysink->zstream; + + /* Initialize compressor object. */ + memset(zs, 0, sizeof(z_stream)); + zs->zalloc = gzip_palloc; + zs->zfree = gzip_pfree; + zs->next_out = (uint8 *) sink->bbs_next->bbs_buffer; + zs->avail_out = sink->bbs_next->bbs_buffer_length; + + /* + * We need to use deflateInit2() rather than deflateInit() here so that + * we can request a gzip header rather than a zlib header. Otherwise, we + * want to supply the same values that would have been used by default + * if we had just called deflateInit(). + * + * Per the documentation for deflateInit2, the third argument must be + * Z_DEFLATED; the fourth argument is the number of "window bits", by + * default 15, but adding 16 gets you a gzip header rather than a zlib + * header; the fifth argument controls memory usage, and 8 is the default; + * and likewise Z_DEFAULT_STRATEGY is the default for the sixth argument. + */ + if (deflateInit2(zs, mysink->compresslevel, Z_DEFLATED, 15 + 16, 8, + Z_DEFAULT_STRATEGY) != Z_OK) + ereport(ERROR, + errcode(ERRCODE_INTERNAL_ERROR), + errmsg("could not initialize compression library")); + + /* + * Add ".gz" to the archive name. Note that the pg_basebackup -z + * produces archives named ".tar.gz" rather than ".tgz", so we match + * that here. + */ + gz_archive_name = psprintf("%s.gz", archive_name); + Assert(sink->bbs_next != NULL); + bbsink_begin_archive(sink->bbs_next, gz_archive_name); + pfree(gz_archive_name); +} + +/* + * Compress the input data to the output buffer until we run out of input + * data. Each time the output buffer fills up, invoke the archive_contents() + * method for then next sink. + * + * Note that since we're compressing the input, it may very commonly happen + * that we consume all the input data without filling the output buffer. In + * that case, the compressed representation of the current input data won't + * actually be sent to the next bbsink until a later call to this function, + * or perhaps even not until bbsink_gzip_end_archive() is invoked. + */ +static void +bbsink_gzip_archive_contents(bbsink *sink, size_t len) +{ + bbsink_gzip *mysink = (bbsink_gzip *) sink; + z_stream *zs = &mysink->zstream; + + /* Compress data from input buffer. */ + zs->next_in = (uint8 *) mysink->base.bbs_buffer; + zs->avail_in = len; + + while (zs->avail_in > 0) + { + int res; + + /* Write output data into unused portion of output buffer. */ + Assert(mysink->bytes_written < mysink->base.bbs_next->bbs_buffer_length); + zs->next_out = (uint8 *) + mysink->base.bbs_next->bbs_buffer + mysink->bytes_written; + zs->avail_out = + mysink->base.bbs_next->bbs_buffer_length - mysink->bytes_written; + + /* + * Try to compress. Note that this will update zs->next_in and + * zs->avail_in according to how much input data was consumed, and + * zs->next_out and zs->avail_out according to how many output bytes + * were produced. + * + * According to the zlib documentation, Z_STREAM_ERROR should only + * occur if we've made a programming error, or if say there's been a + * memory clobber; we use elog() rather than Assert() here out of an + * abundance of caution. + */ + res = deflate(zs, Z_NO_FLUSH); + if (res == Z_STREAM_ERROR) + elog(ERROR, "could not compress data: %s", zs->msg); + + /* Update our notion of how many bytes we've written. */ + mysink->bytes_written = + mysink->base.bbs_next->bbs_buffer_length - zs->avail_out; + + /* + * If the output buffer is full, it's time for the next sink to + * process the contents. + */ + if (mysink->bytes_written >= mysink->base.bbs_next->bbs_buffer_length) + { + bbsink_archive_contents(sink->bbs_next, mysink->bytes_written); + mysink->bytes_written = 0; + } + } +} + +/* + * There might be some data inside zlib's internal buffers; we need to get + * that flushed out and forwarded to the successor sink as archive content. + * + * Then we can end processing for this archive. + */ +static void +bbsink_gzip_end_archive(bbsink *sink) +{ + bbsink_gzip *mysink = (bbsink_gzip *) sink; + z_stream *zs = &mysink->zstream; + + /* There is no more data available. */ + zs->next_in = (uint8 *) mysink->base.bbs_buffer; + zs->avail_in = 0; + + while (1) + { + int res; + + /* Write output data into unused portion of output buffer. */ + Assert(mysink->bytes_written < mysink->base.bbs_next->bbs_buffer_length); + zs->next_out = (uint8 *) + mysink->base.bbs_next->bbs_buffer + mysink->bytes_written; + zs->avail_out = + mysink->base.bbs_next->bbs_buffer_length - mysink->bytes_written; + + /* + * As bbsink_gzip_archive_contents, but pass Z_FINISH since there + * is no more input. + */ + res = deflate(zs, Z_FINISH); + if (res == Z_STREAM_ERROR) + elog(ERROR, "could not compress data: %s", zs->msg); + + /* Update our notion of how many bytes we've written. */ + mysink->bytes_written = + mysink->base.bbs_next->bbs_buffer_length - zs->avail_out; + + /* + * Apparently we had no data in the output buffer and deflate() + * was not able to add any. We must be done. + */ + if (mysink->bytes_written == 0) + break; + + /* Send whatever accumulated output bytes we have. */ + bbsink_archive_contents(sink->bbs_next, mysink->bytes_written); + mysink->bytes_written = 0; + } + + /* Must also pass on the information that this archive has ended. */ + bbsink_forward_end_archive(sink); +} + +/* + * Manifest contents are not compressed, but we do need to copy them into + * the successor sink's buffer, because we have our own. + */ +static void +bbsink_gzip_manifest_contents(bbsink *sink, size_t len) +{ + memcpy(sink->bbs_next->bbs_buffer, sink->bbs_buffer, len); + bbsink_manifest_contents(sink->bbs_next, len); +} + +/* + * Wrapper function to adjust the signature of palloc to match what libz + * expects. + */ +static void * +gzip_palloc(void *opaque, unsigned items, unsigned size) +{ + return palloc(items * size); +} + +/* + * Wrapper function to adjust the signature of pfree to match what libz + * expects. + */ +static void +gzip_pfree(void *opaque, void *address) +{ + pfree(address); +} + +#endif diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index ec3b4f3c17..6ee49a5672 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -139,6 +139,7 @@ static bool verify_checksums = true; static bool manifest = true; static bool manifest_force_encode = false; static char *manifest_checksums = NULL; +static char *server_compression = NULL; static bool success = false; static bool made_new_pgdata = false; @@ -373,13 +374,15 @@ usage(void) " (in kB/s, or use suffix \"k\" or \"M\")\n")); printf(_(" -R, --write-recovery-conf\n" " write configuration for replication\n")); + printf(_(" --server-compression=none|gzip|gzip[1-9]\n" + " compress backup on server\n")); printf(_(" -T, --tablespace-mapping=OLDDIR=NEWDIR\n" " relocate tablespace in OLDDIR to NEWDIR\n")); printf(_(" --waldir=WALDIR location for the write-ahead log directory\n")); printf(_(" -X, --wal-method=none|fetch|stream\n" " include required WAL files with specified method\n")); - printf(_(" -z, --gzip compress tar output\n")); - printf(_(" -Z, --compress=0-9 compress tar output with given compression level\n")); + printf(_(" -z, --gzip compress tar output on client\n")); + printf(_(" -Z, --compress=0-9 compress tar output on client with given compression level\n")); printf(_("\nGeneral options:\n")); printf(_(" -c, --checkpoint=fast|spread\n" " set fast or spread checkpointing\n")); @@ -999,7 +1002,9 @@ CreateBackupStreamer(char *archive_name, char *spclocation, bbstreamer *streamer; bbstreamer *manifest_inject_streamer = NULL; bool inject_manifest; + bool is_tar; bool must_parse_archive; + int archive_name_len = strlen(archive_name); /* * Normally, we emit the backup manifest as a separate file, but when @@ -1008,13 +1013,32 @@ CreateBackupStreamer(char *archive_name, char *spclocation, */ inject_manifest = (format == 't' && strcmp(basedir, "-") == 0 && manifest); + /* Is this a tar archive? */ + is_tar = (archive_name_len > 4 && + strcmp(archive_name + archive_name_len - 4, ".tar") == 0); + /* * We have to parse the archive if (1) we're suppose to extract it, or if * (2) we need to inject backup_manifest or recovery configuration into it. + * However, we only know how to parse tar archives. */ must_parse_archive = (format == 'p' || inject_manifest || (spclocation == NULL && writerecoveryconf)); + /* At present, we only know how to parse tar archives. */ + if (must_parse_archive && !is_tar) + { + pg_log_error("unable to parse archive: %s", archive_name); + pg_log_info("only tar archives can be parsed"); + if (format == 'p') + pg_log_info("plain format requires pg_basebackup to parse the archive"); + if (inject_manifest) + pg_log_info("using - as the output directory requires pg_basebackup to parse the archive"); + if (writerecoveryconf) + pg_log_info("the -R option requires pg_basebackup to parse the archive"); + exit(1); + } + if (format == 'p') { const char *directory; @@ -1754,6 +1778,17 @@ BaseBackup(void) AppendStringCommandOption(&buf, use_new_option_syntax, "TARGET", "client"); + if (server_compression != NULL) + { + if (!use_new_option_syntax) + { + pg_log_error("server does not support server-side compression"); + exit(1); + } + AppendStringCommandOption(&buf, use_new_option_syntax, + "COMPRESSION", server_compression); + } + if (verbose) pg_log_info("initiating base backup, waiting for checkpoint to complete"); @@ -2164,6 +2199,7 @@ main(int argc, char **argv) {"no-manifest", no_argument, NULL, 5}, {"manifest-force-encode", no_argument, NULL, 6}, {"manifest-checksums", required_argument, NULL, 7}, + {"server-compression", required_argument, NULL, 8}, {NULL, 0, NULL, 0} }; int c; @@ -2343,6 +2379,9 @@ main(int argc, char **argv) case 7: manifest_checksums = pg_strdup(optarg); break; + case 8: + server_compression = pg_strdup(optarg); + break; default: /* diff --git a/src/include/replication/basebackup_sink.h b/src/include/replication/basebackup_sink.h index 4acadf406d..d3276b2487 100644 --- a/src/include/replication/basebackup_sink.h +++ b/src/include/replication/basebackup_sink.h @@ -284,6 +284,7 @@ extern void bbsink_forward_cleanup(bbsink *sink); /* Constructors for various types of sinks. */ extern bbsink *bbsink_copystream_new(bool send_to_client); extern bbsink *bbsink_copytblspc_new(void); +extern bbsink *bbsink_gzip_new(bbsink *next, int compresslevel); extern bbsink *bbsink_progress_new(bbsink *next, bool estimate_backup_size); extern bbsink *bbsink_server_new(bbsink *next, char *pathname); extern bbsink *bbsink_throttle_new(bbsink *next, uint32 maxrate); -- 2.24.3 (Apple Git-128) [application/octet-stream] v12-0003-Test-server-side-backup-backup-compression-and-p.patch (4.4K, ../../CA+TgmobQYkP81QQgS6tvvt4cRxvmipHQ4eU-aNjSpiZJhdkckA@mail.gmail.com/3-v12-0003-Test-server-side-backup-backup-compression-and-p.patch) download | inline diff: From 4054ad2eb75f18e7f1349a7db6b6e5828c320d63 Mon Sep 17 00:00:00 2001 From: Robert Haas <[email protected]> Date: Wed, 19 Jan 2022 15:37:27 -0500 Subject: [PATCH v12 3/3] Test server-side backup, backup compression, and pg_verifybackup. --- src/bin/pg_verifybackup/Makefile | 7 ++ src/bin/pg_verifybackup/t/008_untar.pl | 104 +++++++++++++++++++++++++ 2 files changed, 111 insertions(+) create mode 100644 src/bin/pg_verifybackup/t/008_untar.pl diff --git a/src/bin/pg_verifybackup/Makefile b/src/bin/pg_verifybackup/Makefile index c07643b129..1ae818f9a1 100644 --- a/src/bin/pg_verifybackup/Makefile +++ b/src/bin/pg_verifybackup/Makefile @@ -3,6 +3,13 @@ PGFILEDESC = "pg_verifybackup - verify a backup against using a backup manifest" PGAPPICON = win32 +# make these available to TAP test scripts +export TAR +# Note that GZIP cannot be used directly as this environment variable is +# used by the command "gzip" to pass down options, so stick with a different +# name. +export GZIP_PROGRAM=$(GZIP) + subdir = src/bin/pg_verifybackup top_builddir = ../../.. include $(top_builddir)/src/Makefile.global diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl new file mode 100644 index 0000000000..85946cf380 --- /dev/null +++ b/src/bin/pg_verifybackup/t/008_untar.pl @@ -0,0 +1,104 @@ +# Copyright (c) 2021-2022, PostgreSQL Global Development Group + +# This test case aims to verify that server-side backups and server-side +# backup compression work properly, and it also aims to verify that +# pg_verifybackup can verify a base backup that didn't start out in plain +# format. + +use strict; +use warnings; +use Config; +use File::Path qw(rmtree); +use PostgreSQL::Test::Cluster; +use PostgreSQL::Test::Utils; +use Test::More tests => 6; + +my $primary = PostgreSQL::Test::Cluster->new('primary'); +$primary->init(allows_streaming => 1); +$primary->start; + +my $have_zlib = check_pg_config("#define HAVE_LIBZ 1"); +my $backup_path = $primary->backup_dir . '/server-backup'; +my $extract_path = $primary->backup_dir . '/extracted-backup'; + +my @test_configuration = ( + { + 'compression_method' => 'none', + 'backup_flags' => [], + 'backup_archive' => 'base.tar', + 'enabled' => 1 + }, + { + 'compression_method' => 'gzip', + 'backup_flags' => ['--server-compress', 'gzip'], + 'backup_archive' => 'base.tar.gz', + 'decompress_program' => $ENV{'GZIP_PROGRAM'}, + 'decompress_flags' => [ '-d' ], + 'enabled' => check_pg_config("#define HAVE_LIBZ 1") + } +); + +for my $tc (@test_configuration) +{ + my $method = $tc->{'compression_method'}; + + SKIP: { + skip "$method compression not supported by this build", 3 + if ! $tc->{'enabled'}; + skip "no decompressor available for $method", 3 + if exists $tc->{'decompress_program'} && + !defined $tc->{'decompress_program'}; + + # Take a server-side backup. + my @backup = ( + 'pg_basebackup', '--no-sync', '-cfast', '--target', + "server:$backup_path", '-Xfetch' + ); + push @backup, @{$tc->{'backup_flags'}}; + $primary->command_ok(\@backup, + "server side backup, compression $method"); + + + # Verify that the we got the files we expected. + my $backup_files = join(',', + sort grep { $_ ne '.' && $_ ne '..' } slurp_dir($backup_path)); + my $expected_backup_files = join(',', + sort ('backup_manifest', $tc->{'backup_archive'})); + is($backup_files,$expected_backup_files, + "found expected backup files, compression $method"); + + # Decompress. + if (exists $tc->{'decompress_program'}) + { + my @decompress = ($tc->{'decompress_program'}); + push @decompress, @{$tc->{'decompress_flags'}} + if $tc->{'decompress_flags'}; + push @decompress, $backup_path . '/' . $tc->{'backup_archive'}; + system_or_bail(@decompress); + } + + SKIP: { + my $tar = $ENV{TAR}; + # don't check for a working tar here, to accomodate various odd + # cases such as AIX. If tar doesn't work the init_from_backup below + # will fail. + skip "no tar program available", 1 + if (!defined $tar || $tar eq ''); + + # Untar. + mkdir($extract_path); + system_or_bail($tar, 'xf', $backup_path . '/base.tar', + '-C', $extract_path); + + # Verify. + $primary->command_ok([ 'pg_verifybackup', '-n', + '-m', "$backup_path/backup_manifest", '-e', $extract_path ], + "verify backup, compression $method"); + } + + # Cleanup. + unlink($backup_path . '/backup_manifest'); + unlink($backup_path . '/base.tar'); + rmtree($extract_path); + } +} -- 2.24.3 (Apple Git-128) [application/octet-stream] v12-0001-Support-base-backup-targets.patch (38.5K, ../../CA+TgmobQYkP81QQgS6tvvt4cRxvmipHQ4eU-aNjSpiZJhdkckA@mail.gmail.com/4-v12-0001-Support-base-backup-targets.patch) download | inline diff: From 21dbbdf9ee7125f98aff2deb4ebcf401b6414dad Mon Sep 17 00:00:00 2001 From: Robert Haas <[email protected]> Date: Tue, 16 Nov 2021 15:20:50 -0500 Subject: [PATCH v12 1/3] Support base backup targets. pg_basebackup now has a --target=TARGET[:DETAIL] option. If specfied, it is sent to the server as the value of the TARGET option to the BASE_BACKUP command. If DETAIL is included, it is sent as the value of the new TARGET_DETAIL option to the BASE_BACKUP command. If the target is anything other than 'client', pg_basebackup assumes that it will now be the server's job to write the backup in a location somehow defined by the target, and that it therefore needs to write nothing locally. However, the server will still send messages to the client for progress reporting purposes. On the server side, we now support two additional types of backup targets. There is a 'blackhole' target, which just throws away the backup data without doing anything at all with it. Naturally, this should only be used for testing and debugging purposes, since you will not actually have a backup when it finishes running. More usefully, there is also a 'server' target, so you can now use something like 'pg_basebackup -Xnone -t server:/SOME/PATH' to write a backup to some location on the server. Since WAL fetching is handled with separate client-side logic, it's not part of this mechanism; thus, backups with non-default targets, at least for now, must use -Xnone. Patch by me, with a bug fix by Jeevan Ladhe. --- doc/src/sgml/protocol.sgml | 23 +- doc/src/sgml/ref/pg_basebackup.sgml | 30 ++ src/backend/replication/Makefile | 1 + src/backend/replication/basebackup.c | 81 ++++- src/backend/replication/basebackup_copy.c | 21 +- src/backend/replication/basebackup_server.c | 302 +++++++++++++++++++ src/backend/utils/activity/wait_event.c | 6 + src/bin/pg_basebackup/pg_basebackup.c | 208 ++++++++++--- src/bin/pg_basebackup/t/010_pg_basebackup.pl | 64 +++- src/include/replication/basebackup_sink.h | 3 +- src/include/utils/wait_event.h | 2 + 11 files changed, 677 insertions(+), 64 deletions(-) create mode 100644 src/backend/replication/basebackup_server.c diff --git a/doc/src/sgml/protocol.sgml b/doc/src/sgml/protocol.sgml index 7e59edb1cc..cd6dca691e 100644 --- a/doc/src/sgml/protocol.sgml +++ b/doc/src/sgml/protocol.sgml @@ -2640,8 +2640,27 @@ The commands accepted in replication mode are: </para> <para> - At present, the only supported value for this parameter is - <literal>client</literal>. + If the target is <literal>client</literal>, the backup data is + sent to the client. If it is <literal>server</literal>, the backup + data is written to the server at the pathname specified by the + <literal>TARGET_DETAIL</literal> option. If it is + <literal>blackhole</literal>, the backup data is not sent + anywhere; it is simply discarded. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><literal>TARGET_DETAIL</literal> <replaceable>'detail'</replaceable></term> + <listitem> + <para> + Provides additional information about the backup target. + </para> + + <para> + Currently, this option can only be used when the backup target is + <literal>server</literal>. It specifies the server directory + to which the backup should be written. </para> </listitem> </varlistentry> diff --git a/doc/src/sgml/ref/pg_basebackup.sgml b/doc/src/sgml/ref/pg_basebackup.sgml index 9e6807b457..165a9ea5cc 100644 --- a/doc/src/sgml/ref/pg_basebackup.sgml +++ b/doc/src/sgml/ref/pg_basebackup.sgml @@ -224,6 +224,36 @@ PostgreSQL documentation </listitem> </varlistentry> + <varlistentry> + <term><option>-t <replaceable class="parameter">target</replaceable></option></term> + <term><option>--target=<replaceable class="parameter">target</replaceable></option></term> + <listitem> + + <para> + Instructs the server where to place the base backup. The default target + is <literal>client</literal>, which specifies that the backup should + be sent to the machine where <application>pg_basebackup</application> + is running. If the target is instead set to + <literal>server:/some/path</literal>, the backup will be stored on + the machine where the server is running in the + <literal>/some/path</literal> directory. Storing a backup on the + server requires superuser privileges. If the target is set to + <literal>blackhole</literal> causes the contents of the backup to be + discarded and not stored anywhere. This should only be used for + testing purposes, as you will not end up with an actual backup. + </para> + + <para> + Since WAL streaming is implemented by + <application>pg_basebackup</application> rather than by the server, + this option cannot be used together with <literal>-Xstream</literal>. + Since that is the default, when this option is specified, you must also + specify either <literal>-Xfetch</literal> or <literal>-Xnone</literal>. + </para> + + </listitem> + </varlistentry> + <varlistentry> <term><option>-T <replaceable class="parameter">olddir</replaceable>=<replaceable class="parameter">newdir</replaceable></option></term> <term><option>--tablespace-mapping=<replaceable class="parameter">olddir</replaceable>=<replaceable class="parameter">newdir</replaceable></option></term> diff --git a/src/backend/replication/Makefile b/src/backend/replication/Makefile index 74b97cf126..a8f4757f0c 100644 --- a/src/backend/replication/Makefile +++ b/src/backend/replication/Makefile @@ -19,6 +19,7 @@ OBJS = \ basebackup.o \ basebackup_copy.o \ basebackup_progress.o \ + basebackup_server.o \ basebackup_sink.o \ basebackup_throttle.o \ repl_gram.o \ diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c index 3afbbe7e02..d32da51535 100644 --- a/src/backend/replication/basebackup.c +++ b/src/backend/replication/basebackup.c @@ -55,8 +55,10 @@ typedef enum { + BACKUP_TARGET_BLACKHOLE, BACKUP_TARGET_COMPAT, - BACKUP_TARGET_CLIENT + BACKUP_TARGET_CLIENT, + BACKUP_TARGET_SERVER } backup_target_type; typedef struct @@ -69,6 +71,7 @@ typedef struct uint32 maxrate; bool sendtblspcmapfile; backup_target_type target; + char *target_detail; backup_manifest_option manifest; pg_checksum_type manifest_checksum_type; } basebackup_options; @@ -702,6 +705,8 @@ parse_basebackup_options(List *options, basebackup_options *opt) bool o_manifest = false; bool o_manifest_checksums = false; bool o_target = false; + bool o_target_detail = false; + char *target_str = "compat"; /* placate compiler */ MemSet(opt, 0, sizeof(*opt)); opt->target = BACKUP_TARGET_COMPAT; @@ -847,25 +852,35 @@ parse_basebackup_options(List *options, basebackup_options *opt) } else if (strcmp(defel->defname, "target") == 0) { - char *optval = defGetString(defel); + target_str = defGetString(defel); if (o_target) ereport(ERROR, (errcode(ERRCODE_SYNTAX_ERROR), errmsg("duplicate option \"%s\"", defel->defname))); - if (strcmp(optval, "client") == 0) + if (strcmp(target_str, "blackhole") == 0) + opt->target = BACKUP_TARGET_BLACKHOLE; + else if (strcmp(target_str, "client") == 0) opt->target = BACKUP_TARGET_CLIENT; + else if (strcmp(target_str, "server") == 0) + opt->target = BACKUP_TARGET_SERVER; else ereport(ERROR, (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("unrecognized target: \"%s\"", optval))); + errmsg("unrecognized target: \"%s\"", target_str))); o_target = true; } - else - ereport(ERROR, - errcode(ERRCODE_SYNTAX_ERROR), - errmsg("option \"%s\" not recognized", - defel->defname)); + else if (strcmp(defel->defname, "target_detail") == 0) + { + char *optval = defGetString(defel); + + if (o_target_detail) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("duplicate option \"%s\"", defel->defname))); + opt->target_detail = optval; + o_target_detail = true; + } } if (opt->label == NULL) opt->label = "base backup"; @@ -877,6 +892,22 @@ parse_basebackup_options(List *options, basebackup_options *opt) errmsg("manifest checksums require a backup manifest"))); opt->manifest_checksum_type = CHECKSUM_TYPE_NONE; } + if (opt->target == BACKUP_TARGET_SERVER) + { + if (opt->target_detail == NULL) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("target '%s' requires a target detail", + target_str))); + } + else + { + if (opt->target_detail != NULL) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("target '%s' does not accept a target detail", + target_str))); + } } @@ -908,14 +939,38 @@ SendBaseBackup(BaseBackupCmd *cmd) /* * If the TARGET option was specified, then we can use the new copy-stream - * protocol. If not, we must fall back to the old and less capable - * copy-tablespace protocol. + * protocol. If the target is specifically 'client' then set up to stream + * the backup to the client; otherwise, it's being sent someplace else and + * should not be sent to the client. + * + * If the TARGET option was not specified, we must fall back to the older + * and less capable copy-tablespace protocol. */ - if (opt.target != BACKUP_TARGET_COMPAT) - sink = bbsink_copystream_new(); + if (opt.target == BACKUP_TARGET_CLIENT) + sink = bbsink_copystream_new(true); + else if (opt.target != BACKUP_TARGET_COMPAT) + sink = bbsink_copystream_new(false); else sink = bbsink_copytblspc_new(); + /* + * If a non-default backup target is in use, arrange to send the data + * wherever it needs to go. + */ + switch (opt.target) + { + case BACKUP_TARGET_BLACKHOLE: + /* Nothing to do, just discard data. */ + break; + case BACKUP_TARGET_COMPAT: + case BACKUP_TARGET_CLIENT: + /* Nothing to do, handling above is sufficient. */ + break; + case BACKUP_TARGET_SERVER: + sink = bbsink_server_new(sink, opt.target_detail); + break; + } + /* Set up network throttling, if client requested it */ if (opt.maxrate > 0) sink = bbsink_throttle_new(sink, opt.maxrate); diff --git a/src/backend/replication/basebackup_copy.c b/src/backend/replication/basebackup_copy.c index 8dfdff0644..938e19a6a4 100644 --- a/src/backend/replication/basebackup_copy.c +++ b/src/backend/replication/basebackup_copy.c @@ -44,6 +44,9 @@ typedef struct bbsink_copystream /* Common information for all types of sink. */ bbsink base; + /* Are we sending the archives to the client, or somewhere else? */ + bool send_to_client; + /* * Protocol message buffer. We assemble CopyData protocol messages by * setting the first character of this buffer to 'd' (archive or manifest @@ -131,11 +134,12 @@ const bbsink_ops bbsink_copytblspc_ops = { * Create a new 'copystream' bbsink. */ bbsink * -bbsink_copystream_new(void) +bbsink_copystream_new(bool send_to_client) { bbsink_copystream *sink = palloc0(sizeof(bbsink_copystream)); *((const bbsink_ops **) &sink->base.bbs_ops) = &bbsink_copystream_ops; + sink->send_to_client = send_to_client; /* Set up for periodic progress reporting. */ sink->last_progress_report_time = GetCurrentTimestamp(); @@ -212,8 +216,12 @@ bbsink_copystream_archive_contents(bbsink *sink, size_t len) StringInfoData buf; uint64 targetbytes; - /* Send the archive content to the client (with leading type byte). */ - pq_putmessage('d', mysink->msgbuffer, len + 1); + /* Send the archive content to the client, if appropriate. */ + if (mysink->send_to_client) + { + /* Add one because we're also sending a leading type byte. */ + pq_putmessage('d', mysink->msgbuffer, len + 1); + } /* Consider whether to send a progress report to the client. */ targetbytes = mysink->bytes_done_at_last_time_check @@ -294,8 +302,11 @@ bbsink_copystream_manifest_contents(bbsink *sink, size_t len) { bbsink_copystream *mysink = (bbsink_copystream *) sink; - /* Send the manifest content to the client (with leading type byte). */ - pq_putmessage('d', mysink->msgbuffer, len + 1); + if (mysink->send_to_client) + { + /* Add one because we're also sending a leading type byte. */ + pq_putmessage('d', mysink->msgbuffer, len + 1); + } } /* diff --git a/src/backend/replication/basebackup_server.c b/src/backend/replication/basebackup_server.c new file mode 100644 index 0000000000..ce1b7b4797 --- /dev/null +++ b/src/backend/replication/basebackup_server.c @@ -0,0 +1,302 @@ +/*------------------------------------------------------------------------- + * + * basebackup_server.c + * store basebackup archives on the server + * + * IDENTIFICATION + * src/backend/replication/basebackup_server.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "miscadmin.h" +#include "replication/basebackup.h" +#include "replication/basebackup_sink.h" +#include "storage/fd.h" +#include "utils/timestamp.h" +#include "utils/wait_event.h" + +typedef struct bbsink_server +{ + /* Common information for all types of sink. */ + bbsink base; + + /* Directory in which backup is to be stored. */ + char *pathname; + + /* Currently open file (or 0 if nothing open). */ + File file; + + /* Current file position. */ + off_t filepos; +} bbsink_server; + +static void bbsink_server_begin_archive(bbsink *sink, + const char *archive_name); +static void bbsink_server_archive_contents(bbsink *sink, size_t len); +static void bbsink_server_end_archive(bbsink *sink); +static void bbsink_server_begin_manifest(bbsink *sink); +static void bbsink_server_manifest_contents(bbsink *sink, size_t len); +static void bbsink_server_end_manifest(bbsink *sink); + +const bbsink_ops bbsink_server_ops = { + .begin_backup = bbsink_forward_begin_backup, + .begin_archive = bbsink_server_begin_archive, + .archive_contents = bbsink_server_archive_contents, + .end_archive = bbsink_server_end_archive, + .begin_manifest = bbsink_server_begin_manifest, + .manifest_contents = bbsink_server_manifest_contents, + .end_manifest = bbsink_server_end_manifest, + .end_backup = bbsink_forward_end_backup, + .cleanup = bbsink_forward_cleanup +}; + +/* + * Create a new 'server' bbsink. + */ +bbsink * +bbsink_server_new(bbsink *next, char *pathname) +{ + bbsink_server *sink = palloc0(sizeof(bbsink_server)); + + *((const bbsink_ops **) &sink->base.bbs_ops) = &bbsink_server_ops; + sink->pathname = pathname; + sink->base.bbs_next = next; + + /* Replication permission is not sufficient in this case. */ + if (!superuser()) + ereport(ERROR, + (errcode(ERRCODE_INSUFFICIENT_PRIVILEGE), + errmsg("must be superuser to create server backup"))); + + /* + * It's not a good idea to store your backups in the same directory that + * you're backing up. If we allowed a relative path here, that could easily + * happen accidentally, so we don't. The user could still accomplish the + * same thing by including the absolute path to $PGDATA in the pathname, + * but that's likely an intentional bad decision rather than an accident. + */ + if (!is_absolute_path(pathname)) + ereport(ERROR, + (errcode(ERRCODE_INVALID_NAME), + errmsg("relative path not allowed for server backup"))); + + switch (pg_check_dir(pathname)) + { + case 0: + /* + * Does not exist, so create it using the same permissions we'd use + * for a new subdirectory of the data directory itself. + */ + if (MakePGDirectory(pathname) < 0) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not create directory \"%s\": %m", pathname))); + break; + + case 1: + /* Exists, empty. */ + break; + + case 2: + case 3: + case 4: + /* Exists, not empty. */ + ereport(ERROR, + (errcode(ERRCODE_DUPLICATE_FILE), + errmsg("directory \"%s\" exists but is not empty", + pathname))); + break; + + default: + /* Access problem. */ + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not access directory \"%s\": %m", + pathname))); + } + + return &sink->base; +} + +/* + * Open the correct output file for this archive. + */ +static void +bbsink_server_begin_archive(bbsink *sink, const char *archive_name) +{ + bbsink_server *mysink = (bbsink_server *) sink; + char *filename; + + Assert(mysink->file == 0); + Assert(mysink->filepos == 0); + + filename = psprintf("%s/%s", mysink->pathname, archive_name); + + mysink->file = PathNameOpenFile(filename, + O_CREAT | O_EXCL | O_WRONLY | PG_BINARY); + if (mysink->file <= 0) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not create file \"%s\": %m", filename))); + + pfree(filename); + + bbsink_forward_begin_archive(sink, archive_name); +} + +/* + * Write the data to the output file. + */ +static void +bbsink_server_archive_contents(bbsink *sink, size_t len) +{ + bbsink_server *mysink = (bbsink_server *) sink; + int nbytes; + + nbytes = FileWrite(mysink->file, mysink->base.bbs_buffer, len, + mysink->filepos, WAIT_EVENT_BASEBACKUP_WRITE); + + if (nbytes != len) + { + if (nbytes < 0) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not write file \"%s\": %m", + FilePathName(mysink->file)), + errhint("Check free disk space."))); + /* short write: complain appropriately */ + ereport(ERROR, + (errcode(ERRCODE_DISK_FULL), + errmsg("could not write file \"%s\": wrote only %d of %d bytes at offset %u", + FilePathName(mysink->file), + nbytes, (int) len, (unsigned) mysink->filepos), + errhint("Check free disk space."))); + } + + mysink->filepos += nbytes; + + bbsink_forward_archive_contents(sink, len); +} + +/* + * fsync and close the current output file. + */ +static void +bbsink_server_end_archive(bbsink *sink) +{ + bbsink_server *mysink = (bbsink_server *) sink; + + /* + * We intentionally don't use data_sync_elevel here, because the server + * shouldn't PANIC just because we can't guarantee the the backup has been + * written down to disk. Running recovery won't fix anything in this case + * anyway. + */ + if (FileSync(mysink->file, WAIT_EVENT_BASEBACKUP_SYNC) < 0) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not fsync file \"%s\": %m", + FilePathName(mysink->file)))); + + + /* We're done with this file now. */ + FileClose(mysink->file); + mysink->file = 0; + mysink->filepos = 0; + + bbsink_forward_end_archive(sink); +} + +/* + * Open the output file to which we will write the manifest. + * + * Just like pg_basebackup, we write the manifest first under a temporary + * name and then rename it into place after fsync. That way, if the manifest + * is there and under the correct name, the user can be sure that the backup + * completed. + */ +static void +bbsink_server_begin_manifest(bbsink *sink) +{ + bbsink_server *mysink = (bbsink_server *) sink; + char *tmp_filename; + + Assert(mysink->file == 0); + + tmp_filename = psprintf("%s/backup_manifest.tmp", mysink->pathname); + + mysink->file = PathNameOpenFile(tmp_filename, + O_CREAT | O_EXCL | O_WRONLY | PG_BINARY); + if (mysink->file <= 0) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not create file \"%s\": %m", tmp_filename))); + + pfree(tmp_filename); + + bbsink_forward_begin_manifest(sink); +} + +/* + * Each chunk of manifest data is sent using a CopyData message. + */ +static void +bbsink_server_manifest_contents(bbsink *sink, size_t len) +{ + bbsink_server *mysink = (bbsink_server *) sink; + int nbytes; + + nbytes = FileWrite(mysink->file, mysink->base.bbs_buffer, len, + mysink->filepos, WAIT_EVENT_BASEBACKUP_WRITE); + + if (nbytes != len) + { + if (nbytes < 0) + ereport(ERROR, + (errcode_for_file_access(), + errmsg("could not write file \"%s\": %m", + FilePathName(mysink->file)), + errhint("Check free disk space."))); + /* short write: complain appropriately */ + ereport(ERROR, + (errcode(ERRCODE_DISK_FULL), + errmsg("could not write file \"%s\": wrote only %d of %d bytes at offset %u", + FilePathName(mysink->file), + nbytes, (int) len, (unsigned) mysink->filepos), + errhint("Check free disk space."))); + } + + mysink->filepos += nbytes; + + bbsink_forward_manifest_contents(sink, len); +} + +/* + * fsync the backup manifest, close the file, and then rename it into place. + */ +static void +bbsink_server_end_manifest(bbsink *sink) +{ + bbsink_server *mysink = (bbsink_server *) sink; + char *tmp_filename; + char *filename; + + /* We're done with this file now. */ + FileClose(mysink->file); + mysink->file = 0; + + /* + * Rename it into place. This also fsyncs the temporary file, so we don't + * need to do that here. We don't use data_sync_elevel here for the same + * reasons as in bbsink_server_end_archive. + */ + tmp_filename = psprintf("%s/backup_manifest.tmp", mysink->pathname); + filename = psprintf("%s/backup_manifest", mysink->pathname); + durable_rename(tmp_filename, filename, ERROR); + pfree(filename); + pfree(tmp_filename); + + bbsink_forward_end_manifest(sink); +} diff --git a/src/backend/utils/activity/wait_event.c b/src/backend/utils/activity/wait_event.c index 0f5f18f02e..021b83de7a 100644 --- a/src/backend/utils/activity/wait_event.c +++ b/src/backend/utils/activity/wait_event.c @@ -522,6 +522,12 @@ pgstat_get_wait_io(WaitEventIO w) case WAIT_EVENT_BASEBACKUP_READ: event_name = "BaseBackupRead"; break; + case WAIT_EVENT_BASEBACKUP_SYNC: + event_name = "BaseBackupSync"; + break; + case WAIT_EVENT_BASEBACKUP_WRITE: + event_name = "BaseBackupWrite"; + break; case WAIT_EVENT_BUFFILE_READ: event_name = "BufFileRead"; break; diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index 2a58be638a..ec3b4f3c17 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -115,7 +115,7 @@ typedef enum static char *basedir = NULL; static TablespaceList tablespace_dirs = {NULL, NULL}; static char *xlog_dir = NULL; -static char format = 'p'; /* p(lain)/t(ar) */ +static char format = '\0'; /* p(lain)/t(ar) */ static char *label = "pg_basebackup base backup"; static bool noclean = false; static bool checksum_failure = false; @@ -132,6 +132,7 @@ static pg_time_t last_progress_report = 0; static int32 maxrate = 0; /* no limit by default */ static char *replication_slot = NULL; static bool temp_replication_slot = true; +static char *backup_target = NULL; static bool create_slot = false; static bool no_slot = false; static bool verify_checksums = true; @@ -364,6 +365,8 @@ usage(void) printf(_("Usage:\n")); printf(_(" %s [OPTION]...\n"), progname); printf(_("\nOptions controlling the output:\n")); + printf(_(" -t, --target=TARGET[:DETAIL]\n" + " backup target (if other than client)\n")); printf(_(" -D, --pgdata=DIRECTORY receive base backup into directory\n")); printf(_(" -F, --format=p|t output format (plain (default), tar)\n")); printf(_(" -r, --max-rate=RATE maximum transfer rate to transfer data directory\n" @@ -1232,15 +1235,22 @@ ReceiveArchiveStreamChunk(size_t r, char *copybuf, void *callback_data) } /* - * Create an appropriate backup streamer. We know that - * recovery GUCs are supported, because this protocol can only - * be used on v15+. + * Create an appropriate backup streamer, unless a backup + * target was specified. In that case, it's up to the server + * to put the backup wherever it needs to go. */ - state->streamer = - CreateBackupStreamer(archive_name, - spclocation, - &state->manifest_inject_streamer, - true, false); + if (backup_target == NULL) + { + /* + * We know that recovery GUCs are supported, because this + * protocol can only be used on v15+. + */ + state->streamer = + CreateBackupStreamer(archive_name, + spclocation, + &state->manifest_inject_streamer, + true, false); + } break; } @@ -1312,24 +1322,32 @@ ReceiveArchiveStreamChunk(size_t r, char *copybuf, void *callback_data) GetCopyDataEnd(r, copybuf, cursor); /* - * If we're supposed inject the manifest into the archive, we - * prepare to buffer it in memory; otherwise, we prepare to - * write it to a temporary file. + * If a backup target was specified, figuring out where to put + * the manifest is the server's problem. Otherwise, we need to + * deal with it. */ - if (state->manifest_inject_streamer != NULL) - state->manifest_buffer = createPQExpBuffer(); - else + if (backup_target == NULL) { - snprintf(state->manifest_filename, - sizeof(state->manifest_filename), - "%s/backup_manifest.tmp", basedir); - state->manifest_file = - fopen(state->manifest_filename, "wb"); - if (state->manifest_file == NULL) + /* + * If we're supposed inject the manifest into the archive, + * we prepare to buffer it in memory; otherwise, we + * prepare to write it to a temporary file. + */ + if (state->manifest_inject_streamer != NULL) + state->manifest_buffer = createPQExpBuffer(); + else { - pg_log_error("could not create file \"%s\": %m", - state->manifest_filename); - exit(1); + snprintf(state->manifest_filename, + sizeof(state->manifest_filename), + "%s/backup_manifest.tmp", basedir); + state->manifest_file = + fopen(state->manifest_filename, "wb"); + if (state->manifest_file == NULL) + { + pg_log_error("could not create file \"%s\": %m", + state->manifest_filename); + exit(1); + } } } break; @@ -1698,13 +1716,41 @@ BaseBackup(void) if (manifest) { AppendStringCommandOption(&buf, use_new_option_syntax, "MANIFEST", - manifest_force_encode ? "force-encode" : "yes"); + manifest_force_encode ? "force-encode" : "yes"); if (manifest_checksums != NULL) AppendStringCommandOption(&buf, use_new_option_syntax, - "MANIFEST_CHECKSUMS", manifest_checksums); + "MANIFEST_CHECKSUMS", manifest_checksums); } - if (serverMajor >= 1500) + if (backup_target != NULL) + { + char *colon; + + if (serverMajor < 1500) + { + pg_log_error("backup targets are not supported by this server version"); + exit(1); + } + + AppendPlainCommandOption(&buf, use_new_option_syntax, "TABLESPACE_MAP"); + + if ((colon = strchr(backup_target, ':')) == NULL) + { + AppendStringCommandOption(&buf, use_new_option_syntax, + "TARGET", backup_target); + } + else + { + char *target; + + target = pnstrdup(backup_target, colon - backup_target); + AppendStringCommandOption(&buf, use_new_option_syntax, + "TARGET", target); + AppendStringCommandOption(&buf, use_new_option_syntax, + "TARGET_DETAIL", colon + 1); + } + } + else if (serverMajor >= 1500) AppendStringCommandOption(&buf, use_new_option_syntax, "TARGET", "client"); @@ -1799,8 +1845,13 @@ BaseBackup(void) * Verify tablespace directories are empty. Don't bother with the * first once since it can be relocated, and it will be checked before * we do anything anyway. + * + * Note that this is skipped for tar format backups and backups that + * the server is storing to a target location, since in that case + * we won't be storing anything into these directories and thus should + * not create them. */ - if (format == 'p' && !PQgetisnull(res, i, 1)) + if (backup_target == NULL && format == 'p' && !PQgetisnull(res, i, 1)) { char *path = unconstify(char *, get_tablespace_mapping(PQgetvalue(res, i, 1))); @@ -1811,7 +1862,8 @@ BaseBackup(void) /* * When writing to stdout, require a single tablespace */ - writing_to_stdout = format == 't' && strcmp(basedir, "-") == 0; + writing_to_stdout = format == 't' && basedir != NULL && + strcmp(basedir, "-") == 0; if (writing_to_stdout && PQntuples(res) > 1) { pg_log_error("can only write single tablespace to stdout, database has %d", @@ -1894,7 +1946,7 @@ BaseBackup(void) res = PQgetResult(conn); if (PQresultStatus(res) != PGRES_TUPLES_OK) { - pg_log_error("could not get write-ahead log end position from server: %s", + pg_log_error("backup failed: %s", PQerrorMessage(conn)); exit(1); } @@ -2028,8 +2080,11 @@ BaseBackup(void) * synced after being completed. In plain format, all the data of the * base directory is synced, taking into account all the tablespaces. * Errors are not considered fatal. + * + * If, however, there's a backup target, we're not writing anything + * locally, so in that case we skip this step. */ - if (do_sync) + if (do_sync && backup_target == NULL) { if (verbose) pg_log_info("syncing data to disk ..."); @@ -2051,7 +2106,7 @@ BaseBackup(void) * without a backup_manifest file, decreasing the chances that a directory * we leave behind will be mistaken for a valid backup. */ - if (!writing_to_stdout && manifest) + if (!writing_to_stdout && manifest && backup_target == NULL) { char tmp_filename[MAXPGPATH]; char filename[MAXPGPATH]; @@ -2085,6 +2140,7 @@ main(int argc, char **argv) {"max-rate", required_argument, NULL, 'r'}, {"write-recovery-conf", no_argument, NULL, 'R'}, {"slot", required_argument, NULL, 'S'}, + {"target", required_argument, NULL, 't'}, {"tablespace-mapping", required_argument, NULL, 'T'}, {"wal-method", required_argument, NULL, 'X'}, {"gzip", no_argument, NULL, 'z'}, @@ -2135,7 +2191,7 @@ main(int argc, char **argv) atexit(cleanup_directories_atexit); - while ((c = getopt_long(argc, argv, "CD:F:r:RS:T:X:l:nNzZ:d:c:h:p:U:s:wWkvP", + while ((c = getopt_long(argc, argv, "CD:F:r:RS:t:T:X:l:nNzZ:d:c:h:p:U:s:wWkvP", long_options, &option_index)) != -1) { switch (c) @@ -2176,6 +2232,9 @@ main(int argc, char **argv) case 2: no_slot = true; break; + case 't': + backup_target = pg_strdup(optarg); + break; case 'T': tablespace_list_append(optarg); break; @@ -2308,27 +2367,72 @@ main(int argc, char **argv) } /* - * Required arguments + * Setting the backup target to 'client' is equivalent to leaving out the + * option. This logic allows us to assume elsewhere that the backup is + * being stored locally if and only if backup_target == NULL. + */ + if (backup_target != NULL && strcmp(backup_target, "client") == 0) + { + pg_free(backup_target); + backup_target = NULL; + } + + /* + * Can't use --format with --target. Without --target, default format is + * tar. + */ + if (backup_target != NULL && format != '\0') + { + pg_log_error("cannot specify both format and backup target"); + fprintf(stderr, _("Try \"%s --help\" for more information.\n"), + progname); + exit(1); + } + if (format == '\0') + format = 'p'; + + /* + * Either directory or backup target should be specified, but not both */ - if (basedir == NULL) + if (basedir == NULL && backup_target == NULL) { - pg_log_error("no target directory specified"); + pg_log_error("must specify output directory or backup target"); + fprintf(stderr, _("Try \"%s --help\" for more information.\n"), + progname); + exit(1); + } + if (basedir != NULL && backup_target != NULL) + { + pg_log_error("cannot specify both output directory and backup target"); fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); exit(1); } /* - * Mutually exclusive arguments + * Compression doesn't make sense unless tar format is in use. */ if (format == 'p' && compresslevel != 0) { - pg_log_error("only tar mode backups can be compressed"); + if (backup_target == NULL) + pg_log_error("only tar mode backups can be compressed"); + else + pg_log_error("client-side compression is not possible when a backup target is specfied"); fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); exit(1); } + /* + * Sanity checks for WAL method. + */ + if (backup_target != NULL && includewal == STREAM_WAL) + { + pg_log_error("WAL cannot be streamed when a backup target is specified"); + fprintf(stderr, _("Try \"%s --help\" for more information.\n"), + progname); + exit(1); + } if (format == 't' && includewal == STREAM_WAL && strcmp(basedir, "-") == 0) { pg_log_error("cannot stream write-ahead logs in tar mode to stdout"); @@ -2345,6 +2449,9 @@ main(int argc, char **argv) exit(1); } + /* + * Sanity checks for replication slot options. + */ if (no_slot) { if (replication_slot) @@ -2378,8 +2485,18 @@ main(int argc, char **argv) } } + /* + * Sanity checks on WAL directory. + */ if (xlog_dir) { + if (backup_target != NULL) + { + pg_log_error("WAL directory location cannot be specified along with a backup target"); + fprintf(stderr, _("Try \"%s --help\" for more information.\n"), + progname); + exit(1); + } if (format != 'p') { pg_log_error("WAL directory location can only be specified in plain mode"); @@ -2400,6 +2517,7 @@ main(int argc, char **argv) } #ifndef HAVE_LIBZ + /* Sanity checks for compression level. */ if (compresslevel != 0) { pg_log_error("this build does not support compression"); @@ -2407,6 +2525,9 @@ main(int argc, char **argv) } #endif + /* + * Sanity checks for progress reporting options. + */ if (showprogress && !estimatesize) { pg_log_error("%s and %s are incompatible options", @@ -2416,6 +2537,9 @@ main(int argc, char **argv) exit(1); } + /* + * Sanity checks for backup manifest options. + */ if (!manifest && manifest_checksums != NULL) { pg_log_error("%s and %s are incompatible options", @@ -2458,11 +2582,11 @@ main(int argc, char **argv) manifest = false; /* - * Verify that the target directory exists, or create it. For plaintext - * backups, always require the directory. For tar backups, require it - * unless we are writing to stdout. + * If an output directory was specified, verify that it exists, or create + * it. Note that for a tar backup, an output directory of "-" means we are + * writing to stdout, so do nothing in that case. */ - if (format == 'p' || strcmp(basedir, "-") != 0) + if (basedir != NULL && (format == 'p' || strcmp(basedir, "-") != 0)) verify_dir_is_empty_or_create(basedir, &made_new_pgdata, &found_existing_pgdata); /* determine remote server's xlog segment size */ diff --git a/src/bin/pg_basebackup/t/010_pg_basebackup.pl b/src/bin/pg_basebackup/t/010_pg_basebackup.pl index f0243f28d4..f7e21941eb 100644 --- a/src/bin/pg_basebackup/t/010_pg_basebackup.pl +++ b/src/bin/pg_basebackup/t/010_pg_basebackup.pl @@ -10,7 +10,7 @@ use File::Path qw(rmtree); use Fcntl qw(:seek); use PostgreSQL::Test::Cluster; use PostgreSQL::Test::Utils; -use Test::More tests => 115; +use Test::More tests => 135; program_help_ok('pg_basebackup'); program_version_ok('pg_basebackup'); @@ -474,6 +474,68 @@ $node->command_ok( ], 'pg_basebackup -X stream runs with --no-slot'); rmtree("$tempdir/backupnoslot"); +$node->command_ok( + [ @pg_basebackup_defs, '-D', "$tempdir/backupxf", '-X', 'fetch' ], + 'pg_basebackup -X fetch runs'); + +$node->command_fails_like( + [ @pg_basebackup_defs, '--target', 'blackhole' ], + qr/WAL cannot be streamed when a backup target is specified/, + 'backup target requires -X'); +$node->command_fails_like( + [ @pg_basebackup_defs, '--target', 'blackhole', '-X', 'stream' ], + qr/WAL cannot be streamed when a backup target is specified/, + 'backup target requires -X other than -X stream'); +$node->command_fails_like( + [ @pg_basebackup_defs, '--target', 'bogus', '-X', 'none' ], + qr/unrecognized target/, + 'backup target unrecognized'); +$node->command_fails_like( + [ @pg_basebackup_defs, '--target', 'blackhole', '-X', 'none', '-D', "$tempdir/blackhole" ], + qr/cannot specify both output directory and backup target/, + 'backup target and output directory'); +$node->command_fails_like( + [ @pg_basebackup_defs, '--target', 'blackhole', '-X', 'none', '-Ft' ], + qr/cannot specify both format and backup target/, + 'backup target and output directory'); +$node->command_ok( + [ @pg_basebackup_defs, '--target', 'blackhole', '-X', 'none' ], + 'backup target blackhole'); +$node->command_ok( + [ @pg_basebackup_defs, '--target', "server:$tempdir/backuponserver", '-X', 'none' ], + 'backup target server'); +ok(-f "$tempdir/backuponserver/base.tar", 'backup tar was created'); +rmtree("$tempdir/backuponserver"); + +$node->command_fails( + [ + @pg_basebackup_defs, '-D', + "$tempdir/backupxs_sl_fail", '-X', + 'stream', '-S', + 'slot0' + ], + 'pg_basebackup fails with nonexistent replication slot'); + +$node->command_fails( + [ @pg_basebackup_defs, '-D', "$tempdir/backupxs_slot", '-C' ], + 'pg_basebackup -C fails without slot name'); + +$node->command_fails( + [ + @pg_basebackup_defs, '-D', + "$tempdir/backupxs_slot", '-C', + '-S', 'slot0', + '--no-slot' + ], + 'pg_basebackup fails with -C -S --no-slot'); +$node->command_fails_like( + [ @pg_basebackup_defs, '--target', 'blackhole', '-D', "$tempdir/blackhole" ], + qr/cannot specify both output directory and backup target/, + 'backup target and output directory'); + +$node->command_ok( + [ @pg_basebackup_defs, '-D', "$tempdir/backuptr/co", '-X', 'none' ], + 'pg_basebackup -X fetch runs'); $node->command_fails( [ diff --git a/src/include/replication/basebackup_sink.h b/src/include/replication/basebackup_sink.h index 25436defa8..4acadf406d 100644 --- a/src/include/replication/basebackup_sink.h +++ b/src/include/replication/basebackup_sink.h @@ -282,9 +282,10 @@ extern void bbsink_forward_end_backup(bbsink *sink, XLogRecPtr endptr, extern void bbsink_forward_cleanup(bbsink *sink); /* Constructors for various types of sinks. */ -extern bbsink *bbsink_copystream_new(void); +extern bbsink *bbsink_copystream_new(bool send_to_client); extern bbsink *bbsink_copytblspc_new(void); extern bbsink *bbsink_progress_new(bbsink *next, bool estimate_backup_size); +extern bbsink *bbsink_server_new(bbsink *next, char *pathname); extern bbsink *bbsink_throttle_new(bbsink *next, uint32 maxrate); /* Extra interface functions for progress reporting. */ diff --git a/src/include/utils/wait_event.h b/src/include/utils/wait_event.h index e0b2f56f47..395d325c5f 100644 --- a/src/include/utils/wait_event.h +++ b/src/include/utils/wait_event.h @@ -157,6 +157,8 @@ typedef enum typedef enum { WAIT_EVENT_BASEBACKUP_READ = PG_WAIT_IO, + WAIT_EVENT_BASEBACKUP_SYNC, + WAIT_EVENT_BASEBACKUP_WRITE, WAIT_EVENT_BUFFILE_READ, WAIT_EVENT_BUFFILE_WRITE, WAIT_EVENT_BUFFILE_TRUNCATE, -- 2.24.3 (Apple Git-128) ^ permalink raw reply [nested|flat] 203+ messages in thread
* Re: refactoring basebackup.c 2022-01-19 12:16 Re: refactoring basebackup.c Dipesh Pandit <[email protected]> 2022-01-19 21:26 ` Re: refactoring basebackup.c Robert Haas <[email protected]> @ 2022-01-21 18:33 ` Robert Haas <[email protected]> 0 siblings, 0 replies; 203+ messages in thread From: Robert Haas @ 2022-01-21 18:33 UTC (permalink / raw) To: Dipesh Pandit <[email protected]>; Michael Paquier <[email protected]>; +Cc: Jeevan Ladhe <[email protected]>; tushar <[email protected]>; Dmitry Dolgov <[email protected]>; Mark Dilger <[email protected]>; pgsql-hackers On Wed, Jan 19, 2022 at 4:26 PM Robert Haas <[email protected]> wrote: > I spent some time thinking about test coverage for the server-side > backup code today and came up with the attached (v12-0003). I committed the base backup target patch yesterday, and today I updated the remaining code in light of Michael Paquier's commit 5c649fe153367cdab278738ee4aebbfd158e0546. Here is the resulting patch. Michael, I am proposing to that we remove this message as part of this commit: - pg_log_info("no value specified for compression level, switching to default"); I think most people won't want to specify a compression level, so emitting a message when they don't seems too verbose. -- Robert Haas EDB: http://www.enterprisedb.com Attachments: [application/octet-stream] v13-0001-Server-side-gzip-compression.patch (33.0K, ../../CA+Tgmoa-ST7fMLsVJduOB7Eub=2WjfpHS+QxHVEpUoinf4bOSg@mail.gmail.com/2-v13-0001-Server-side-gzip-compression.patch) download | inline diff: From b5c10db6e3eaf62ff18ad7462a26b9916b554307 Mon Sep 17 00:00:00 2001 From: Robert Haas <[email protected]> Date: Fri, 21 Jan 2022 13:29:28 -0500 Subject: [PATCH v13] Server-side gzip compression. pg_basebackup's --compression option now lets you write either "client-gzip" or "server-gzip" instead of just "gzip" to specify where the compression should be performed. If you write simply "gzip" it's taken to mean "client-gzip" unless you also use --target, in which case it is interpreted to mean "server-gzip", because that's the only thing that makes any sense in that case. To make this work, the BASE_BACKUP command now takes new COMPRESSION and COMPRESSION_LEVEL options. At present, pg_basebackup cannot decompress .gz files, so server-side compression will cause a failure if (1) -Ft is not used or (2) -R is used or (3) -D- is used without --no-manifest. Along the way, I removed the information message added by commit 5c649fe153367cdab278738ee4aebbfd158e0546 which occurred if you specified no compression level and told you that the default level had been used instead. That seemed like more output than most people would want. Also along the way, this adds a check to the server for unrecognized base backup options. This repairs a bug introduced by commit 0ba281cb4bf9f5f65529dfa4c8282abb734dd454. This commit also adds some new test cases for pg_verifybackup. They take a server-side backup with and without compression, and then extract the backup if we have the OS facilities available to do so, and then run pg_verifybackup on the extracted directory. That is a good test of the functionality added by this commit and also improves test coverage for the backup target patch (commit 3500ccc39b0dadd1068a03938e4b8ff562587ccc) and for pg_verifybackup itself. Patch by me, with a bug fix by Jeevan Ladhe. The patch set of which this is a part has also had review and/or testing from Tushar Ahuja, Suraj Kharage, Dipesh Pandit, and Mark Dilger. --- doc/src/sgml/protocol.sgml | 22 ++ doc/src/sgml/ref/pg_basebackup.sgml | 29 +- src/backend/Makefile | 2 +- src/backend/replication/Makefile | 1 + src/backend/replication/basebackup.c | 54 ++++ src/backend/replication/basebackup_gzip.c | 309 ++++++++++++++++++++++ src/bin/pg_basebackup/pg_basebackup.c | 136 ++++++++-- src/bin/pg_verifybackup/Makefile | 7 + src/bin/pg_verifybackup/t/008_untar.pl | 104 ++++++++ src/include/replication/basebackup_sink.h | 1 + 10 files changed, 641 insertions(+), 24 deletions(-) create mode 100644 src/backend/replication/basebackup_gzip.c create mode 100644 src/bin/pg_verifybackup/t/008_untar.pl diff --git a/doc/src/sgml/protocol.sgml b/doc/src/sgml/protocol.sgml index cd6dca691e..2d63e0132c 100644 --- a/doc/src/sgml/protocol.sgml +++ b/doc/src/sgml/protocol.sgml @@ -2719,6 +2719,28 @@ The commands accepted in replication mode are: </listitem> </varlistentry> + <varlistentry> + <term><literal>COMPRESSION</literal> <replaceable>'method'</replaceable></term> + <listitem> + <para> + Instructs the server to compress the backup using the specified + method. Currently, the only supported method is + <literal>gzip</literal>. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><literal>COMPRESSION_LEVEL</literal> <replaceable>level</replaceable></term> + <listitem> + <para> + Specifies the compression level to be used. This should only be + used in conjunction with the <literal>COMPRESSION</literal> option. + The value should be an integer between 1 and 9. + </para> + </listitem> + </varlistentry> + <varlistentry> <term><literal>MAX_RATE</literal> <replaceable>rate</replaceable></term> <listitem> diff --git a/doc/src/sgml/ref/pg_basebackup.sgml b/doc/src/sgml/ref/pg_basebackup.sgml index 47d11289be..1d0df346b9 100644 --- a/doc/src/sgml/ref/pg_basebackup.sgml +++ b/doc/src/sgml/ref/pg_basebackup.sgml @@ -400,21 +400,36 @@ PostgreSQL documentation <term><option>-Z <replaceable class="parameter">level</replaceable></option></term> <term><option>-Z <replaceable class="parameter">method</replaceable></option>[:<replaceable>level</replaceable>]</term> <term><option>--compress=<replaceable class="parameter">level</replaceable></option></term> - <term><option>--compress=<replaceable class="parameter">method</replaceable></option>[:<replaceable>level</replaceable>]</term> + <term><option>--compress=[[{<replaceable class="parameter">client|server</replaceable>-}]<replaceable class="parameter">method</replaceable></option>[:<replaceable>level</replaceable>]</term> <listitem> <para> - Enables compression of tar file output, and specifies the - compression level (0 through 9, 0 being no compression and 9 being best - compression). Compression is only available when using the tar - format, and the suffix <filename>.gz</filename> will - automatically be added to all tar filenames. + Requests compression of the backup. If <literal>client</literal> or + <literal>server</literal> is included, it specifies where the + compression is to be performed. Compressing on the server will reduce + transfer bandwidth but will increase server CPU consumption. The + default is <literal>client</literal> except when + <literal>--target</literal> is used. In that case, the backup is not + being sent to the client, so only server compression is sensible. + When <literal>-Xstream</literal>, which is the default, is used, + server-side compression will not be applied to the WAL. To compress + the WAL, use client-side compression, or + specify <literal>-Xfetch</literal>. </para> <para> The compression method can be set to either <literal>gzip</literal> for compression with <application>gzip</application>, or <literal>none</literal> for no compression. A compression level can be optionally specified, by appending the level number after a - colon (<literal>:</literal>). + colon (<literal>:</literal>). If no level is specified, the default + compression level will be used. If only a level is specified without + mentioning an algorithm, <literal>gzip</literal> compression will + be used if the level is greater than 0, and no compression will be + used if the level is 0. + </para> + <para> + When the tar format is used, the suffix <filename>.gz</filename> will + automatically be added to all tar filenames. Compression is not + available in plain format. </para> </listitem> </varlistentry> diff --git a/src/backend/Makefile b/src/backend/Makefile index add9560be4..4a02006788 100644 --- a/src/backend/Makefile +++ b/src/backend/Makefile @@ -48,7 +48,7 @@ OBJS = \ LIBS := $(filter-out -lpgport -lpgcommon, $(LIBS)) $(LDAP_LIBS_BE) $(ICU_LIBS) # The backend doesn't need everything that's in LIBS, however -LIBS := $(filter-out -lz -lreadline -ledit -ltermcap -lncurses -lcurses, $(LIBS)) +LIBS := $(filter-out -lreadline -ledit -ltermcap -lncurses -lcurses, $(LIBS)) ifeq ($(with_systemd),yes) LIBS += -lsystemd diff --git a/src/backend/replication/Makefile b/src/backend/replication/Makefile index a8f4757f0c..8ec60ded76 100644 --- a/src/backend/replication/Makefile +++ b/src/backend/replication/Makefile @@ -18,6 +18,7 @@ OBJS = \ backup_manifest.o \ basebackup.o \ basebackup_copy.o \ + basebackup_gzip.o \ basebackup_progress.o \ basebackup_server.o \ basebackup_sink.o \ diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c index d32da51535..10ce2406c0 100644 --- a/src/backend/replication/basebackup.c +++ b/src/backend/replication/basebackup.c @@ -61,6 +61,12 @@ typedef enum BACKUP_TARGET_SERVER } backup_target_type; +typedef enum +{ + BACKUP_COMPRESSION_NONE, + BACKUP_COMPRESSION_GZIP +} basebackup_compression_type; + typedef struct { const char *label; @@ -73,6 +79,8 @@ typedef struct backup_target_type target; char *target_detail; backup_manifest_option manifest; + basebackup_compression_type compression; + int compression_level; pg_checksum_type manifest_checksum_type; } basebackup_options; @@ -707,11 +715,14 @@ parse_basebackup_options(List *options, basebackup_options *opt) bool o_target = false; bool o_target_detail = false; char *target_str = "compat"; /* placate compiler */ + bool o_compression = false; + bool o_compression_level = false; MemSet(opt, 0, sizeof(*opt)); opt->target = BACKUP_TARGET_COMPAT; opt->manifest = MANIFEST_OPTION_NO; opt->manifest_checksum_type = CHECKSUM_TYPE_CRC32C; + opt->compression = BACKUP_COMPRESSION_NONE; foreach(lopt, options) { @@ -881,7 +892,41 @@ parse_basebackup_options(List *options, basebackup_options *opt) opt->target_detail = optval; o_target_detail = true; } + else if (strcmp(defel->defname, "compression") == 0) + { + char *optval = defGetString(defel); + + if (o_compression) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("duplicate option \"%s\"", defel->defname))); + if (strcmp(optval, "none") == 0) + opt->compression = BACKUP_COMPRESSION_NONE; + else if (strcmp(optval, "gzip") == 0) + opt->compression = BACKUP_COMPRESSION_GZIP; + else + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("unrecognized compression algorithm: \"%s\"", + optval))); + o_compression = true; + } + else if (strcmp(defel->defname, "compression_level") == 0) + { + if (o_compression_level) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("duplicate option \"%s\"", defel->defname))); + opt->compression_level = defGetInt32(defel); + o_compression_level = true; + } + else + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("unrecognized base backup option: \"%s\"", + defel->defname))); } + if (opt->label == NULL) opt->label = "base backup"; if (opt->manifest == MANIFEST_OPTION_NO) @@ -908,6 +953,11 @@ parse_basebackup_options(List *options, basebackup_options *opt) errmsg("target '%s' does not accept a target detail", target_str))); } + + if (o_compression_level && !o_compression) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("compression level requires compression"))); } @@ -975,6 +1025,10 @@ SendBaseBackup(BaseBackupCmd *cmd) if (opt.maxrate > 0) sink = bbsink_throttle_new(sink, opt.maxrate); + /* Set up server-side compression, if client requested it */ + if (opt.compression == BACKUP_COMPRESSION_GZIP) + sink = bbsink_gzip_new(sink, opt.compression_level); + /* Set up progress reporting. */ sink = bbsink_progress_new(sink, opt.progress); diff --git a/src/backend/replication/basebackup_gzip.c b/src/backend/replication/basebackup_gzip.c new file mode 100644 index 0000000000..1e58382fa0 --- /dev/null +++ b/src/backend/replication/basebackup_gzip.c @@ -0,0 +1,309 @@ +/*------------------------------------------------------------------------- + * + * basebackup_gzip.c + * Basebackup sink implementing gzip compression. + * + * Portions Copyright (c) 2010-2020, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/backend/replication/basebackup_gzip.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#ifdef HAVE_LIBZ +#include <zlib.h> +#endif + +#include "replication/basebackup_sink.h" + +#ifdef HAVE_LIBZ +typedef struct bbsink_gzip +{ + /* Common information for all types of sink. */ + bbsink base; + + /* Compression level. */ + int compresslevel; + + /* Compressed data stream. */ + z_stream zstream; + + /* Number of bytes staged in output buffer. */ + size_t bytes_written; +} bbsink_gzip; + +static void bbsink_gzip_begin_backup(bbsink *sink); +static void bbsink_gzip_begin_archive(bbsink *sink, const char *archive_name); +static void bbsink_gzip_archive_contents(bbsink *sink, size_t len); +static void bbsink_gzip_manifest_contents(bbsink *sink, size_t len); +static void bbsink_gzip_end_archive(bbsink *sink); +static void *gzip_palloc(void *opaque, unsigned items, unsigned size); +static void gzip_pfree(void *opaque, void *address); + +const bbsink_ops bbsink_gzip_ops = { + .begin_backup = bbsink_gzip_begin_backup, + .begin_archive = bbsink_gzip_begin_archive, + .archive_contents = bbsink_gzip_archive_contents, + .end_archive = bbsink_gzip_end_archive, + .begin_manifest = bbsink_forward_begin_manifest, + .manifest_contents = bbsink_gzip_manifest_contents, + .end_manifest = bbsink_forward_end_manifest, + .end_backup = bbsink_forward_end_backup, + .cleanup = bbsink_forward_cleanup +}; +#endif + +/* + * Create a new basebackup sink that performs gzip compression using the + * designated compression level. + */ +bbsink * +bbsink_gzip_new(bbsink *next, int compresslevel) +{ +#ifndef HAVE_LIBZ + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("gzip compression is not supported by this build"))); +#else + bbsink_gzip *sink; + + Assert(next != NULL); + Assert(compresslevel >= 0 && compresslevel <= 9); + + if (compresslevel == 0) + compresslevel = Z_DEFAULT_COMPRESSION; + else if (compresslevel < 0 || compresslevel > 9) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("gzip compression level %d is out of range", + compresslevel))); + + sink = palloc0(sizeof(bbsink_gzip)); + *((const bbsink_ops **) &sink->base.bbs_ops) = &bbsink_gzip_ops; + sink->base.bbs_next = next; + sink->compresslevel = compresslevel; + + return &sink->base; +#endif +} + +#ifdef HAVE_LIBZ + +/* + * Begin backup. + */ +static void +bbsink_gzip_begin_backup(bbsink *sink) +{ + /* + * We need our own buffer, because we're going to pass different data to + * the next sink than what gets passed to us. + */ + sink->bbs_buffer = palloc(sink->bbs_buffer_length); + + /* + * Since deflate() doesn't require the output buffer to be of any + * particular size, we can just make it the same size as the input buffer. + */ + bbsink_begin_backup(sink->bbs_next, sink->bbs_state, + sink->bbs_buffer_length); +} + +/* + * Prepare to compress the next archive. + */ +static void +bbsink_gzip_begin_archive(bbsink *sink, const char *archive_name) +{ + bbsink_gzip *mysink = (bbsink_gzip *) sink; + char *gz_archive_name; + z_stream *zs = &mysink->zstream; + + /* Initialize compressor object. */ + memset(zs, 0, sizeof(z_stream)); + zs->zalloc = gzip_palloc; + zs->zfree = gzip_pfree; + zs->next_out = (uint8 *) sink->bbs_next->bbs_buffer; + zs->avail_out = sink->bbs_next->bbs_buffer_length; + + /* + * We need to use deflateInit2() rather than deflateInit() here so that + * we can request a gzip header rather than a zlib header. Otherwise, we + * want to supply the same values that would have been used by default + * if we had just called deflateInit(). + * + * Per the documentation for deflateInit2, the third argument must be + * Z_DEFLATED; the fourth argument is the number of "window bits", by + * default 15, but adding 16 gets you a gzip header rather than a zlib + * header; the fifth argument controls memory usage, and 8 is the default; + * and likewise Z_DEFAULT_STRATEGY is the default for the sixth argument. + */ + if (deflateInit2(zs, mysink->compresslevel, Z_DEFLATED, 15 + 16, 8, + Z_DEFAULT_STRATEGY) != Z_OK) + ereport(ERROR, + errcode(ERRCODE_INTERNAL_ERROR), + errmsg("could not initialize compression library")); + + /* + * Add ".gz" to the archive name. Note that the pg_basebackup -z + * produces archives named ".tar.gz" rather than ".tgz", so we match + * that here. + */ + gz_archive_name = psprintf("%s.gz", archive_name); + Assert(sink->bbs_next != NULL); + bbsink_begin_archive(sink->bbs_next, gz_archive_name); + pfree(gz_archive_name); +} + +/* + * Compress the input data to the output buffer until we run out of input + * data. Each time the output buffer fills up, invoke the archive_contents() + * method for then next sink. + * + * Note that since we're compressing the input, it may very commonly happen + * that we consume all the input data without filling the output buffer. In + * that case, the compressed representation of the current input data won't + * actually be sent to the next bbsink until a later call to this function, + * or perhaps even not until bbsink_gzip_end_archive() is invoked. + */ +static void +bbsink_gzip_archive_contents(bbsink *sink, size_t len) +{ + bbsink_gzip *mysink = (bbsink_gzip *) sink; + z_stream *zs = &mysink->zstream; + + /* Compress data from input buffer. */ + zs->next_in = (uint8 *) mysink->base.bbs_buffer; + zs->avail_in = len; + + while (zs->avail_in > 0) + { + int res; + + /* Write output data into unused portion of output buffer. */ + Assert(mysink->bytes_written < mysink->base.bbs_next->bbs_buffer_length); + zs->next_out = (uint8 *) + mysink->base.bbs_next->bbs_buffer + mysink->bytes_written; + zs->avail_out = + mysink->base.bbs_next->bbs_buffer_length - mysink->bytes_written; + + /* + * Try to compress. Note that this will update zs->next_in and + * zs->avail_in according to how much input data was consumed, and + * zs->next_out and zs->avail_out according to how many output bytes + * were produced. + * + * According to the zlib documentation, Z_STREAM_ERROR should only + * occur if we've made a programming error, or if say there's been a + * memory clobber; we use elog() rather than Assert() here out of an + * abundance of caution. + */ + res = deflate(zs, Z_NO_FLUSH); + if (res == Z_STREAM_ERROR) + elog(ERROR, "could not compress data: %s", zs->msg); + + /* Update our notion of how many bytes we've written. */ + mysink->bytes_written = + mysink->base.bbs_next->bbs_buffer_length - zs->avail_out; + + /* + * If the output buffer is full, it's time for the next sink to + * process the contents. + */ + if (mysink->bytes_written >= mysink->base.bbs_next->bbs_buffer_length) + { + bbsink_archive_contents(sink->bbs_next, mysink->bytes_written); + mysink->bytes_written = 0; + } + } +} + +/* + * There might be some data inside zlib's internal buffers; we need to get + * that flushed out and forwarded to the successor sink as archive content. + * + * Then we can end processing for this archive. + */ +static void +bbsink_gzip_end_archive(bbsink *sink) +{ + bbsink_gzip *mysink = (bbsink_gzip *) sink; + z_stream *zs = &mysink->zstream; + + /* There is no more data available. */ + zs->next_in = (uint8 *) mysink->base.bbs_buffer; + zs->avail_in = 0; + + while (1) + { + int res; + + /* Write output data into unused portion of output buffer. */ + Assert(mysink->bytes_written < mysink->base.bbs_next->bbs_buffer_length); + zs->next_out = (uint8 *) + mysink->base.bbs_next->bbs_buffer + mysink->bytes_written; + zs->avail_out = + mysink->base.bbs_next->bbs_buffer_length - mysink->bytes_written; + + /* + * As bbsink_gzip_archive_contents, but pass Z_FINISH since there + * is no more input. + */ + res = deflate(zs, Z_FINISH); + if (res == Z_STREAM_ERROR) + elog(ERROR, "could not compress data: %s", zs->msg); + + /* Update our notion of how many bytes we've written. */ + mysink->bytes_written = + mysink->base.bbs_next->bbs_buffer_length - zs->avail_out; + + /* + * Apparently we had no data in the output buffer and deflate() + * was not able to add any. We must be done. + */ + if (mysink->bytes_written == 0) + break; + + /* Send whatever accumulated output bytes we have. */ + bbsink_archive_contents(sink->bbs_next, mysink->bytes_written); + mysink->bytes_written = 0; + } + + /* Must also pass on the information that this archive has ended. */ + bbsink_forward_end_archive(sink); +} + +/* + * Manifest contents are not compressed, but we do need to copy them into + * the successor sink's buffer, because we have our own. + */ +static void +bbsink_gzip_manifest_contents(bbsink *sink, size_t len) +{ + memcpy(sink->bbs_next->bbs_buffer, sink->bbs_buffer, len); + bbsink_manifest_contents(sink->bbs_next, len); +} + +/* + * Wrapper function to adjust the signature of palloc to match what libz + * expects. + */ +static void * +gzip_palloc(void *opaque, unsigned items, unsigned size) +{ + return palloc(items * size); +} + +/* + * Wrapper function to adjust the signature of pfree to match what libz + * expects. + */ +static void +gzip_pfree(void *opaque, void *address) +{ + pfree(address); +} + +#endif diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c index d5b0ade10d..6fdd1b9958 100644 --- a/src/bin/pg_basebackup/pg_basebackup.c +++ b/src/bin/pg_basebackup/pg_basebackup.c @@ -111,6 +111,16 @@ typedef enum STREAM_WAL } IncludeWal; +/* + * Different places to perform compression + */ +typedef enum +{ + COMPRESS_LOCATION_UNSPECIFIED, + COMPRESS_LOCATION_CLIENT, + COMPRESS_LOCATION_SERVER +} CompressionLocation; + /* Global options */ static char *basedir = NULL; static TablespaceList tablespace_dirs = {NULL, NULL}; @@ -124,6 +134,7 @@ static bool estimatesize = true; static int verbose = 0; static int compresslevel = 0; static WalCompressionMethod compressmethod = COMPRESSION_NONE; +static CompressionLocation compressloc = COMPRESS_LOCATION_UNSPECIFIED; static IncludeWal includewal = STREAM_WAL; static bool fastcheckpoint = false; static bool writerecoveryconf = false; @@ -544,6 +555,11 @@ LogStreamerMain(logstreamer_param *param) stream.walmethod = CreateWalDirectoryMethod(param->xlog, COMPRESSION_NONE, 0, stream.do_sync); + else if (compressloc != COMPRESS_LOCATION_CLIENT) + stream.walmethod = CreateWalTarMethod(param->xlog, + COMPRESSION_NONE, + compresslevel, + stream.do_sync); else stream.walmethod = CreateWalTarMethod(param->xlog, compressmethod, @@ -944,7 +960,7 @@ parse_max_rate(char *src) */ static void parse_compress_options(char *src, WalCompressionMethod *methodres, - int *levelres) + CompressionLocation *locationres, int *levelres) { char *sep; int firstlen; @@ -967,9 +983,25 @@ parse_compress_options(char *src, WalCompressionMethod *methodres, * compression method. */ if (pg_strcasecmp(firstpart, "gzip") == 0) + { + *methodres = COMPRESSION_GZIP; + *locationres = COMPRESS_LOCATION_UNSPECIFIED; + } + else if (pg_strcasecmp(firstpart, "client-gzip") == 0) + { + *methodres = COMPRESSION_GZIP; + *locationres = COMPRESS_LOCATION_CLIENT; + } + else if (pg_strcasecmp(firstpart, "server-gzip") == 0) + { *methodres = COMPRESSION_GZIP; + *locationres = COMPRESS_LOCATION_SERVER; + } else if (pg_strcasecmp(firstpart, "none") == 0) + { *methodres = COMPRESSION_NONE; + *locationres = COMPRESS_LOCATION_UNSPECIFIED; + } else { /* @@ -983,6 +1015,7 @@ parse_compress_options(char *src, WalCompressionMethod *methodres, *methodres = (*levelres > 0) ? COMPRESSION_GZIP : COMPRESSION_NONE; + *locationres = COMPRESS_LOCATION_UNSPECIFIED; return; } @@ -1075,7 +1108,9 @@ CreateBackupStreamer(char *archive_name, char *spclocation, bbstreamer *streamer = NULL; bbstreamer *manifest_inject_streamer = NULL; bool inject_manifest; + bool is_tar; bool must_parse_archive; + int archive_name_len = strlen(archive_name); /* * Normally, we emit the backup manifest as a separate file, but when @@ -1084,13 +1119,32 @@ CreateBackupStreamer(char *archive_name, char *spclocation, */ inject_manifest = (format == 't' && strcmp(basedir, "-") == 0 && manifest); + /* Is this a tar archive? */ + is_tar = (archive_name_len > 4 && + strcmp(archive_name + archive_name_len - 4, ".tar") == 0); + /* * We have to parse the archive if (1) we're suppose to extract it, or if * (2) we need to inject backup_manifest or recovery configuration into it. + * However, we only know how to parse tar archives. */ must_parse_archive = (format == 'p' || inject_manifest || (spclocation == NULL && writerecoveryconf)); + /* At present, we only know how to parse tar archives. */ + if (must_parse_archive && !is_tar) + { + pg_log_error("unable to parse archive: %s", archive_name); + pg_log_info("only tar archives can be parsed"); + if (format == 'p') + pg_log_info("plain format requires pg_basebackup to parse the archive"); + if (inject_manifest) + pg_log_info("using - as the output directory requires pg_basebackup to parse the archive"); + if (writerecoveryconf) + pg_log_info("the -R option requires pg_basebackup to parse the archive"); + exit(1); + } + if (format == 'p') { const char *directory; @@ -1131,7 +1185,8 @@ CreateBackupStreamer(char *archive_name, char *spclocation, archive_file = NULL; } - if (compressmethod == COMPRESSION_NONE) + if (compressmethod == COMPRESSION_NONE || + compressloc != COMPRESS_LOCATION_CLIENT) streamer = bbstreamer_plain_writer_new(archive_filename, archive_file); #ifdef HAVE_LIBZ @@ -1833,6 +1888,31 @@ BaseBackup(void) AppendStringCommandOption(&buf, use_new_option_syntax, "TARGET", "client"); + if (compressloc == COMPRESS_LOCATION_SERVER) + { + char *compressmethodstr = NULL; + + if (!use_new_option_syntax) + { + pg_log_error("server does not support server-side compression"); + exit(1); + } + switch (compressmethod) + { + case COMPRESSION_GZIP: + compressmethodstr = "gzip"; + break; + default: + Assert(false); + break; + } + AppendStringCommandOption(&buf, use_new_option_syntax, + "COMPRESSION", compressmethodstr); + if (compresslevel != 0) + AppendIntegerCommandOption(&buf, use_new_option_syntax, + "COMPRESSION_LEVEL", compresslevel); + } + if (verbose) pg_log_info("initiating base backup, waiting for checkpoint to complete"); @@ -2359,10 +2439,11 @@ main(int argc, char **argv) compresslevel = 1; /* will be rejected below */ #endif compressmethod = COMPRESSION_GZIP; + compressloc = COMPRESS_LOCATION_UNSPECIFIED; break; case 'Z': parse_compress_options(optarg, &compressmethod, - &compresslevel); + &compressloc, &compresslevel); break; case 'c': if (pg_strcasecmp(optarg, "fast") == 0) @@ -2489,14 +2570,37 @@ main(int argc, char **argv) } /* - * Compression doesn't make sense unless tar format is in use. + * If we're compressing the backup and the user has not said where to + * perform the compression, do it on the client, unless they specified + * --target, in which case the server is the only choice. */ - if (format == 'p' && compressmethod != COMPRESSION_NONE) + if (compressmethod != COMPRESSION_NONE && + compressloc == COMPRESS_LOCATION_UNSPECIFIED) { if (backup_target == NULL) - pg_log_error("only tar mode backups can be compressed"); + compressloc = COMPRESS_LOCATION_CLIENT; else - pg_log_error("client-side compression is not possible when a backup target is specfied"); + compressloc = COMPRESS_LOCATION_SERVER; + } + + /* + * Can't perform client-side compression if the backup is not being + * sent to the client. + */ + if (backup_target != NULL && compressloc == COMPRESS_LOCATION_CLIENT) + { + pg_log_error("client-side compression is not possible when a backup target is specified"); + fprintf(stderr, _("Try \"%s --help\" for more information.\n"), + progname); + exit(1); + } + + /* + * Compression doesn't make sense unless tar format is in use. + */ + if (format == 'p' && compressloc == COMPRESS_LOCATION_CLIENT) + { + pg_log_error("only tar mode backups can be compressed"); fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname); exit(1); @@ -2609,23 +2713,23 @@ main(int argc, char **argv) } break; case COMPRESSION_GZIP: -#ifdef HAVE_LIBZ - if (compresslevel == 0) - { - pg_log_info("no value specified for compression level, switching to default"); - compresslevel = Z_DEFAULT_COMPRESSION; - } if (compresslevel > 9) { pg_log_error("compression level %d of method %s higher than maximum of 9", compresslevel, "gzip"); exit(1); } + if (compressloc == COMPRESS_LOCATION_CLIENT) + { +#ifdef HAVE_LIBZ + if (compresslevel == 0) + compresslevel = Z_DEFAULT_COMPRESSION; #else - pg_log_error("this build does not support compression with %s", - "gzip"); - exit(1); + pg_log_error("this build does not support compression with %s", + "gzip"); + exit(1); #endif + } break; case COMPRESSION_LZ4: /* option not supported */ diff --git a/src/bin/pg_verifybackup/Makefile b/src/bin/pg_verifybackup/Makefile index c07643b129..1ae818f9a1 100644 --- a/src/bin/pg_verifybackup/Makefile +++ b/src/bin/pg_verifybackup/Makefile @@ -3,6 +3,13 @@ PGFILEDESC = "pg_verifybackup - verify a backup against using a backup manifest" PGAPPICON = win32 +# make these available to TAP test scripts +export TAR +# Note that GZIP cannot be used directly as this environment variable is +# used by the command "gzip" to pass down options, so stick with a different +# name. +export GZIP_PROGRAM=$(GZIP) + subdir = src/bin/pg_verifybackup top_builddir = ../../.. include $(top_builddir)/src/Makefile.global diff --git a/src/bin/pg_verifybackup/t/008_untar.pl b/src/bin/pg_verifybackup/t/008_untar.pl new file mode 100644 index 0000000000..1d74a41886 --- /dev/null +++ b/src/bin/pg_verifybackup/t/008_untar.pl @@ -0,0 +1,104 @@ +# Copyright (c) 2021-2022, PostgreSQL Global Development Group + +# This test case aims to verify that server-side backups and server-side +# backup compression work properly, and it also aims to verify that +# pg_verifybackup can verify a base backup that didn't start out in plain +# format. + +use strict; +use warnings; +use Config; +use File::Path qw(rmtree); +use PostgreSQL::Test::Cluster; +use PostgreSQL::Test::Utils; +use Test::More tests => 6; + +my $primary = PostgreSQL::Test::Cluster->new('primary'); +$primary->init(allows_streaming => 1); +$primary->start; + +my $have_zlib = check_pg_config("#define HAVE_LIBZ 1"); +my $backup_path = $primary->backup_dir . '/server-backup'; +my $extract_path = $primary->backup_dir . '/extracted-backup'; + +my @test_configuration = ( + { + 'compression_method' => 'none', + 'backup_flags' => [], + 'backup_archive' => 'base.tar', + 'enabled' => 1 + }, + { + 'compression_method' => 'gzip', + 'backup_flags' => ['--compress', 'server-gzip'], + 'backup_archive' => 'base.tar.gz', + 'decompress_program' => $ENV{'GZIP_PROGRAM'}, + 'decompress_flags' => [ '-d' ], + 'enabled' => check_pg_config("#define HAVE_LIBZ 1") + } +); + +for my $tc (@test_configuration) +{ + my $method = $tc->{'compression_method'}; + + SKIP: { + skip "$method compression not supported by this build", 3 + if ! $tc->{'enabled'}; + skip "no decompressor available for $method", 3 + if exists $tc->{'decompress_program'} && + !defined $tc->{'decompress_program'}; + + # Take a server-side backup. + my @backup = ( + 'pg_basebackup', '--no-sync', '-cfast', '--target', + "server:$backup_path", '-Xfetch' + ); + push @backup, @{$tc->{'backup_flags'}}; + $primary->command_ok(\@backup, + "server side backup, compression $method"); + + + # Verify that the we got the files we expected. + my $backup_files = join(',', + sort grep { $_ ne '.' && $_ ne '..' } slurp_dir($backup_path)); + my $expected_backup_files = join(',', + sort ('backup_manifest', $tc->{'backup_archive'})); + is($backup_files,$expected_backup_files, + "found expected backup files, compression $method"); + + # Decompress. + if (exists $tc->{'decompress_program'}) + { + my @decompress = ($tc->{'decompress_program'}); + push @decompress, @{$tc->{'decompress_flags'}} + if $tc->{'decompress_flags'}; + push @decompress, $backup_path . '/' . $tc->{'backup_archive'}; + system_or_bail(@decompress); + } + + SKIP: { + my $tar = $ENV{TAR}; + # don't check for a working tar here, to accomodate various odd + # cases such as AIX. If tar doesn't work the init_from_backup below + # will fail. + skip "no tar program available", 1 + if (!defined $tar || $tar eq ''); + + # Untar. + mkdir($extract_path); + system_or_bail($tar, 'xf', $backup_path . '/base.tar', + '-C', $extract_path); + + # Verify. + $primary->command_ok([ 'pg_verifybackup', '-n', + '-m', "$backup_path/backup_manifest", '-e', $extract_path ], + "verify backup, compression $method"); + } + + # Cleanup. + unlink($backup_path . '/backup_manifest'); + unlink($backup_path . '/base.tar'); + rmtree($extract_path); + } +} diff --git a/src/include/replication/basebackup_sink.h b/src/include/replication/basebackup_sink.h index 4acadf406d..d3276b2487 100644 --- a/src/include/replication/basebackup_sink.h +++ b/src/include/replication/basebackup_sink.h @@ -284,6 +284,7 @@ extern void bbsink_forward_cleanup(bbsink *sink); /* Constructors for various types of sinks. */ extern bbsink *bbsink_copystream_new(bool send_to_client); extern bbsink *bbsink_copytblspc_new(void); +extern bbsink *bbsink_gzip_new(bbsink *next, int compresslevel); extern bbsink *bbsink_progress_new(bbsink *next, bool estimate_backup_size); extern bbsink *bbsink_server_new(bbsink *next, char *pathname); extern bbsink *bbsink_throttle_new(bbsink *next, uint32 maxrate); -- 2.24.3 (Apple Git-128) ^ permalink raw reply [nested|flat] 203+ messages in thread
end of thread, other threads:[~2022-01-21 18:33 UTC | newest] Thread overview: 203+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v30 3/6] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v35 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v32 3/6] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v31 3/6] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v29 3/6] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v33 3/5] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v32 3/6] Subscripting for jsonb erthalion <[email protected]> 2019-02-01 10:41 [PATCH v34 3/5] Subscripting for jsonb erthalion <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v39] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v38] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v40 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v45 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v43 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v46 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v42 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v41 1/2] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v44 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v48 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2020-12-18 16:19 [PATCH v49 1/3] Subscripting for jsonb Dmitrii Dolgov <[email protected]> 2022-01-19 12:16 Re: refactoring basebackup.c Dipesh Pandit <[email protected]> 2022-01-19 15:56 ` Re: refactoring basebackup.c Robert Haas <[email protected]> 2022-01-19 21:26 ` Re: refactoring basebackup.c Robert Haas <[email protected]> 2022-01-21 18:33 ` Re: refactoring basebackup.c Robert Haas <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox